跳转至

ExcelMaster

通用 Excel 报告引擎 —— 封装 xlsxwriter，提供光标流式写入 + 图表 + 条件格式。

格式定义 — ExcelFormatTool

ExcelFormatTool

ExcelFormat

Initialize excel format.

源代码位于： ExcelMaster/ExcelFormatTool.py 
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
class ExcelFormat:
    '''
    Initialize excel format.

    '''

    def __init__(self, filepath):
        '''
        This creates the workbook using the filename specified in
        filename_workbook.

        '''

        self.engine = pd.ExcelWriter(filepath, engine='xlsxwriter')
        self.workbook = self.engine.book
        self.basename = os.path.basename(filepath)
        self.base_filepath = filepath.strip(self.basename)


        ######### Basic Text-related Formatting ###############

        self.dict_cell_format = {}

        self.TEXT_NO_FORMAT = self.workbook.add_format({'font_name': 'Calibri', 'font_size': 11})
        self.dict_cell_format['TEXT_NO_FORMAT'] = self.TEXT_NO_FORMAT
        self.dict_cell_format[''] = self.TEXT_NO_FORMAT

        self.HEADER_1 = self.workbook.add_format({
            'bold': True,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 18,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_1'] = self.HEADER_1
        self.dict_cell_format['#'] = self.HEADER_1

        self.HEADER_2 = self.workbook.add_format({
            'bold': True,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 16,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_2'] = self.HEADER_2
        self.dict_cell_format['##'] = self.HEADER_2

        self.HEADER_3 = self.workbook.add_format({
            'bold': True,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 14,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_3'] = self.HEADER_3
        self.dict_cell_format['###'] = self.HEADER_3

        self.HEADER_4 = self.workbook.add_format({
            'bold': True,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 12,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_4'] = self.HEADER_4
        self.dict_cell_format['####'] = self.HEADER_4

        self.HEADER_1I = self.workbook.add_format({
            'bold': True,
            'underline': True,            
            'font_name': 'Calibri',
            'font_size': 18,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_1I'] = self.HEADER_1I
        self.dict_cell_format['#_'] = self.HEADER_1I

        self.HEADER_2I = self.workbook.add_format({
            'bold': True,
            'underline': True,            
            'font_name': 'Calibri',
            'font_size': 16,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_2I'] = self.HEADER_2I
        self.dict_cell_format['##_'] = self.HEADER_2I

        self.HEADER_3I = self.workbook.add_format({
            'bold': True,
            'underline': True,            
            'font_name': 'Calibri',
            'font_size': 14,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_3I'] = self.HEADER_3I
        self.dict_cell_format['###_'] = self.HEADER_3I

        self.HEADER_4I = self.workbook.add_format({
            'bold': True,
            'underline': True,            
            'font_name': 'Calibri',
            'font_size': 12,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['HEADER_4I'] = self.HEADER_4I
        self.dict_cell_format['####_'] = self.HEADER_4I

        self.TEXT_BOLD = self.workbook.add_format({
            'bold': True,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'align': 'left'
        })
        self.dict_cell_format['TEXT_BOLD'] = self.TEXT_BOLD
        self.dict_cell_format['B'] = self.TEXT_BOLD
        self.dict_cell_format['**'] = self.TEXT_BOLD

        self.TEXT_ITALIC = self.workbook.add_format({
            'bold': False,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'align': 'left',
            'italic': True
        })
        self.dict_cell_format['TEXT_ITALIC'] = self.TEXT_ITALIC
        self.dict_cell_format['I'] = self.TEXT_ITALIC
        self.dict_cell_format['*'] = self.TEXT_ITALIC

        self.TEXT_UNDERLINE = self.workbook.add_format({
            'bold': False,
            'underline': True,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'align': 'left',
            'italic': False
        })
        self.dict_cell_format['TEXT_UNDERLINE'] = self.TEXT_UNDERLINE
        self.dict_cell_format['U'] = self.TEXT_UNDERLINE
        self.dict_cell_format['_'] = self.TEXT_UNDERLINE

        self.TEXT_NO_FORMAT_BORDER = self.workbook.add_format({
            'bold': False,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'align': 'left',
            'border': 1
        })
        self.dict_cell_format['TEXT_NO_FORMAT_BORDER'] = self.TEXT_NO_FORMAT_BORDER  
        self.dict_cell_format['BORDER'] = self.TEXT_NO_FORMAT_BORDER
        self.dict_cell_format['----'] = self.TEXT_NO_FORMAT_BORDER

        self.TEXT_BORDER_CENTER = self.workbook.add_format({
            'bold': False,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'align': 'center',
            'valign': 'vcenter',
            'border': 1
        })
        self.dict_cell_format['TEXT_BORDER_CENTER'] = self.TEXT_BORDER_CENTER  
        self.dict_cell_format['BORDER_CENTER'] = self.TEXT_BORDER_CENTER
        self.dict_cell_format['----C'] = self.TEXT_BORDER_CENTER

        self.TEXT_RED = self.workbook.add_format({
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#FF3800',
            'align': 'left'
        })
        self.dict_cell_format['TEXT_RED'] = self.TEXT_RED
        self.dict_cell_format['RED'] = self.TEXT_RED

        self.TEXT_RED_BOLD = self.workbook.add_format({
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#FF3800',
            "bold": True,
            'align': 'left'
        })
        self.dict_cell_format['TEXT_RED_BOLD'] = self.TEXT_RED_BOLD
        self.dict_cell_format['**RED'] = self.TEXT_RED_BOLD

        self.TEXT_BOLD_UNDERLINE = self.workbook.add_format({
            'bold': True,
            'underline': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'align': 'left'
        })
        self.dict_cell_format['TEXT_BOLD_UNDERLINE'] = self.TEXT_BOLD_UNDERLINE
        self.dict_cell_format['BU'] = self.TEXT_BOLD_UNDERLINE
        self.dict_cell_format['**_'] = self.TEXT_BOLD_UNDERLINE

        self.TEXT_ITALIC_UNDERLINE = self.workbook.add_format({
            'bold': False,
            'underline': True,
            'italic': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'align': 'left'
        })
        self.dict_cell_format['TEXT_ITALIC_UNDERLINE'] = self.TEXT_ITALIC_UNDERLINE
        self.dict_cell_format['IU'] = self.TEXT_ITALIC_UNDERLINE
        self.dict_cell_format['*_'] = self.TEXT_ITALIC_UNDERLINE

        self.TEXT_BOLD_ITALIC_UNDERLINE = self.workbook.add_format({
            'bold': True,
            'underline': True,
            'italic': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'align': 'left'
        })
        self.dict_cell_format['TEXT_BOLD_ITALIC_UNDERLINE'] = self.TEXT_BOLD_ITALIC_UNDERLINE
        self.dict_cell_format['BIU'] = self.TEXT_BOLD_ITALIC_UNDERLINE
        self.dict_cell_format['***_'] = self.TEXT_BOLD_ITALIC_UNDERLINE

        self.HEADER_3_BOLD_UNDERLINE = self.workbook.add_format({
            'bold': True,
            'underline': True,
            'font_name': 'Calibri',
            'font_size': 14,
            'align': 'left'
        })
        self.dict_cell_format['HEADER_4_BOLD_UNDERLINE'] = self.HEADER_3_BOLD_UNDERLINE
        self.dict_cell_format['H3_BU'] = self.HEADER_3_BOLD_UNDERLINE
        self.dict_cell_format['####**_'] = self.HEADER_3_BOLD_UNDERLINE

        self.HEADER_4_BOLD_UNDERLINE = self.workbook.add_format({
            'bold': True,
            'underline': True,
            'font_name': 'Calibri',
            'font_size': 12,
            'align': 'left'
        })
        self.dict_cell_format['HEADER_4_BOLD_UNDERLINE'] = self.HEADER_4_BOLD_UNDERLINE
        self.dict_cell_format['H4_BU'] = self.HEADER_4_BOLD_UNDERLINE
        self.dict_cell_format['####**_'] = self.HEADER_4_BOLD_UNDERLINE

        self.TEXT_NO_FORMAT_PERCENTAGE = self.workbook.add_format({
            'bold': False,
            'underline': False,            
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            'num_format': '0.0000%',
            'align': 'left',    
            'border': 1
        })
        self.dict_cell_format['TEXT_NO_FORMAT_PERCENTAGE'] = self.TEXT_NO_FORMAT_PERCENTAGE
        self.dict_cell_format['NUM_PERCENTAGE'] = self.TEXT_NO_FORMAT_PERCENTAGE
        self.dict_cell_format['%'] = self.TEXT_NO_FORMAT_PERCENTAGE

        self.TEXT_SECTION_HEADER = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 12,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'center',
            'valign': 'vcenter',
            'text_wrap': False
        })
        self.dict_cell_format['TEXT_SECTION_HEADER'] = self.TEXT_SECTION_HEADER
        self.dict_cell_format['SECTION'] = self.TEXT_SECTION_HEADER

        self.TEXT_ITALIC_10 = self.workbook.add_format({
            'italic': True,
            'font_name': 'Calibri',
            'font_size': 10,
            'align': 'left'
        })
        self.dict_cell_format['TEXT_ITALIC_10'] = self.TEXT_ITALIC_10

        ######### Basic Text-related Formatting (END) ###############


        ######### TABLE HEADER FORMATTING  ##########################

        self.TABLE_ROW_COL_HEADER = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#1F4994',
            'align': 'left',
            'border': 1
        })
        self.dict_cell_format['ROW_COL_HEADER'] = self.TABLE_ROW_COL_HEADER

        self.TABLE_HEADER = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#000000',
            # No 'bg_color' key = no fill. xlsxwriter >= 3.2 rejects None via
            # Color._from_value(None) -> TypeError, so omit the key entirely.
            'align': 'center',
            'valign': 'vcenter',
            'text_wrap': False,
            'border': 1
        })
        self.dict_cell_format['TABLE_HEADER'] = self.TABLE_HEADER
        self.dict_cell_format['HEADER'] = self.TABLE_HEADER

        ######### TABLE HEADER FORMATTING (END)  ##########################

        ######## Colored Title Formatting #################################

        self.BG_BOLD_ORANGE_H4 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 12,
            'font_color': '#000000',
            'bg_color': '#FABF8F',
            'align': 'center',
            'border': 1
        })
        self.dict_cell_format['BG_BOLD_ORANGE_H4'] = self.BG_BOLD_ORANGE_H4
        self.dict_cell_format['ORANGE_H4'] = self.BG_BOLD_ORANGE_H4

        self.BG_BOLD_ORANGE_H3 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 14,
            'font_color': '#000000',
            'bg_color': '#FABF8F',
            'align': 'center',
            'border': 1
        })
        self.dict_cell_format['BG_BOLD_ORANGE_H3'] = self.BG_BOLD_ORANGE_H3
        self.dict_cell_format['ORANGE_H3'] = self.BG_BOLD_ORANGE_H3

        self.BG_BOLD_ORANGE_H2 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 16,
            'font_color': '#000000',
            'bg_color': '#FABF8F',
            'align': 'center',
            'border': 1
        })
        self.dict_cell_format['BG_BOLD_ORANGE_H2'] = self.BG_BOLD_ORANGE_H2
        self.dict_cell_format['ORANGE_H2'] = self.BG_BOLD_ORANGE_H2

        self.BG_BOLD_ORANGE_H1 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 18,
            'font_color': '#000000',
            'bg_color': '#FABF8F',
            'align': 'center',
            'border': 1
        })
        self.dict_cell_format['BG_BOLD_ORANGE_H1'] = self.BG_BOLD_ORANGE_H1
        self.dict_cell_format['ORANGE_H1'] = self.BG_BOLD_ORANGE_H1

        self.BG_FONT_BLUE_H4 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 12,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'center'  ,
            'border': 1
        })
        self.dict_cell_format['BG_FONT_BLUE_H4'] = self.BG_FONT_BLUE_H4
        self.dict_cell_format['BLUE_H4'] = self.BG_FONT_BLUE_H4

        self.BG_FONT_BLUE_H3 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 14,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'center'  ,
            'border': 1
        })
        self.dict_cell_format['BG_FONT_BLUE_H3'] = self.BG_FONT_BLUE_H3
        self.dict_cell_format['BLUE_H3'] = self.BG_FONT_BLUE_H3

        self.BG_FONT_BLUE_H2 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 16,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'center'  ,
            'border': 1
        })
        self.dict_cell_format['BG_FONT_BLUE_H2'] = self.BG_FONT_BLUE_H2
        self.dict_cell_format['BLUE_H2'] = self.BG_FONT_BLUE_H2

        self.BG_FONT_BLUE_H1 = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 18,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'center'  ,
            'border': 1
        })
        self.dict_cell_format['BG_FONT_BLUE_H1'] = self.BG_FONT_BLUE_H1
        self.dict_cell_format['BLUE_H1'] = self.BG_FONT_BLUE_H1

        ########## Colored Title Formatting (END) #################################

        self.SECTION_HEADER_PERCENTAGE = self.workbook.add_format({
            'bold': True,
            'font_name': 'Calibri',
            'font_size': 11,
            'font_color': '#1F497D',
            'bg_color': '#C5D9F1',
            'align': 'left',
            'valign': 'vcenter',
            'text_wrap': True,
            'border': 1,
            'num_format': '0.0000%',
        })
        self.dict_cell_format['SECTION_HEADER_PERCENTAGE'] = self.SECTION_HEADER_PERCENTAGE  
        self.dict_cell_format['SECTION%'] = self.SECTION_HEADER_PERCENTAGE

        self.TEXT_RIGHT_JUSTIFY = self.workbook.add_format({
            'font_name': 'Calibri',
            'font_size': 11,
            'align': 'right'
        })
        self.dict_cell_format['TEXT_RIGHT_JUSTIFY'] = self.TEXT_RIGHT_JUSTIFY    
        self.dict_cell_format['TEXT_RIGHT'] = self.TEXT_RIGHT_JUSTIFY

        ################# Number Formatting #################
        self.NUM_COMMA = self.workbook.add_format({'num_format': '#,##0', 'border': 1})
        self.dict_cell_format['NUM_COMMA'] = self.NUM_COMMA  
        self.dict_cell_format['NUM,'] = self.NUM_COMMA

        self.NUM_PERCENTAGE = self.workbook.add_format({'num_format': "0.0000%", 'border': 1})
        self.dict_cell_format['NUM_PERCENTAGE'] = self.NUM_PERCENTAGE  
        self.dict_cell_format['NUM%.4'] = self.NUM_PERCENTAGE

        self.NUM_PERCENTAGE = self.workbook.add_format({'num_format': "0.000%", 'border': 1})
        self.dict_cell_format['NUM_PERCENTAGE'] = self.NUM_PERCENTAGE  
        self.dict_cell_format['NUM%.3'] = self.NUM_PERCENTAGE

        self.NUM_PERCENTAGE = self.workbook.add_format({'num_format': "0.00%", 'border': 1})
        self.dict_cell_format['NUM_PERCENTAGE'] = self.NUM_PERCENTAGE  
        self.dict_cell_format['NUM%.2'] = self.NUM_PERCENTAGE

        self.NUM_PERCENTAGE = self.workbook.add_format({'num_format': "0.0%", 'border': 1})
        self.dict_cell_format['NUM_PERCENTAGE'] = self.NUM_PERCENTAGE  
        self.dict_cell_format['NUM%.1'] = self.NUM_PERCENTAGE


        ################# Highlight Formatting #################
        self.BG_LIGHT_YELLOW = self.workbook.add_format({"bg_color": "fcfc81"})
        self.dict_cell_format['BG_LIGHT_YELLOW'] = self.BG_LIGHT_YELLOW  
        self.dict_cell_format['YELLOW_BG'] = self.BG_LIGHT_YELLOW

    def add_new_format(self, format_dict, format_name):
        """ Add a new user-defined format. """
        if format_name not in self.dict_cell_format.keys():
            self.dict_cell_format[format_name] = self.workbook.add_format(format_dict)
            return 0
        logger.info("ERROR: Failed to add new format, the format name has already existed!")
        return 1

add_new_format 

add_new_format(format_dict, format_name)

Add a new user-defined format.

源代码位于： ExcelMaster/ExcelFormatTool.py 
481
482
483
484
485
486
487
def add_new_format(self, format_dict, format_name):
    """ Add a new user-defined format. """
    if format_name not in self.dict_cell_format.keys():
        self.dict_cell_format[format_name] = self.workbook.add_format(format_dict)
        return 0
    logger.info("ERROR: Failed to add new format, the format name has already existed!")
    return 1

核心引擎 — ExcelMaster

ExcelMaster

ExcelWorkbook

Bases: ExcelFormat

Write anything to Excel (Workbook-level Operator).

源代码位于： ExcelMaster/ExcelMaster.py 
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
class ExcelWorkbook(ExcelFormat):
    """ Write anything to Excel (Workbook-level Operator). """
    def __init__(self, filepath, verbose = True):
        super().__init__(filepath)
        self.verbose = verbose
        self.ws_dict = {}

    def to_cell_range_text(self, first_row, first_col, last_row, last_col):
        """ To Excel Cell Range. """
        return xl_range(first_row, first_col, last_row, last_col)

    def cell_range_to_loc(self, cell_range_text):
        """ Convert text cell range expression to a list of values. """
        cell_range_list = cell_range_text.split(":")
        res = []
        for x in cell_range_list:
            res += list(xl_cell_to_rowcol(x))
        return res

    def colletter_to_textloc(self, row_index, col_letter):
        """ Append Row Index to the given Column Letter-Formatted Index. """
        col_letter = col_letter if ":" in col_letter else (col_letter + ":" + col_letter)
        output = col_letter.split(":")
        output = ":".join([col + str(row_index) for col in output])
        return output

    def set_color_scale(self, worksheet, cell_range,
                        colors = ("#F8696B", "#FFEB84", "#63BE7B")):
        """ Set Color Scale. """
        if len(colors) == 3:
            f = {
                    "type": "3_color_scale",
                    "min_color": colors[0],
                    "mid_color": colors[1],
                    "max_color": colors[2],
                }
        elif len(colors) == 2:
            f = {
                    "type": "2_color_scale",
                    "min_color": colors[0],
                    "max_color": colors[1],
                }
        else:
            raise ValueError("Please give 2 or 3 colors!")

        if isinstance(cell_range, list) or isinstance(cell_range, tuple):
            cell_range = self.to_cell_range_text(*cell_range)

        worksheet.conditional_format(cell_range, f)
        return 0

    def set_data_bar(self, worksheet, cell_range, bar_color = "#63C384"):
        """ Set Data Bar in a Worksheet for a range of cells. """

        f = {'type': 'data_bar',
             'data_bar_2010': True,
             "bar_color": bar_color}

        if isinstance(cell_range, list) or isinstance(cell_range, tuple):
            cell_range = self.to_cell_range_text(*cell_range)

        worksheet.conditional_format(cell_range, f)
        return 0

    def set_cell_format(self, worksheet, cell_range, cformat, cell_condition = None):
        """ Set format for a range of cell. """

        if cell_condition and isinstance(cell_condition, tuple):
            criteria = cell_condition[0].lower()
            value = cell_condition[1]

        if isinstance(cell_range, list) or isinstance(cell_range, tuple):
            cell_range = self.to_cell_range_text(*cell_range)

        if isinstance(cformat, str):
            cformat = self.dict_cell_format[cformat]

        if cell_condition and isinstance(cell_condition, tuple):

            if (criteria == 'between') or (criteria == 'not between'):
                worksheet.conditional_format(cell_range, {"type": "cell", 
                                                          "criteria": criteria, 
                                                          "minimum": value[0],
                                                          "maximum": value[1], 
                                                          "format": cformat})

                return 0

            worksheet.conditional_format(cell_range, {"type": "cell", 
                                                      "criteria": criteria, 
                                                      "value": value, 
                                                      "format": cformat})
            return 0

        worksheet.conditional_format(cell_range, {'type': 'no_errors', "format": cformat}) 
        return 0

    def set_cell_format_rbyr(self, worksheet, start_row, condition_list, condition, ifelse_col, cformat = "YELLOW_BG"):
        """ Conditionally Highlight Cells Row by Row. """

        if_col = ifelse_col[0]
        else_col = ifelse_col[1]

        i = 0
        row_concur = start_row
        while i < len(condition_list):
            target = condition_list[i]

            if val_input_condition(target, condition):
                if if_col:
                    self.set_cell_format(worksheet, 
                                       cell_range=self.colletter_to_textloc(row_concur + 1, if_col), 
                                       cformat=cformat)

            else:
                if else_col:
                    self.set_cell_format(worksheet, 
                                       cell_range=self.colletter_to_textloc(row_concur + 1, else_col), 
                                       cformat=cformat)

            i += 1
            row_concur = row_concur + 1
        return 0

    def remove_tmp_img(self, img_pattern = r".tmp_image_[0-9]+.png"):
        """ Remove Temp Images. """
        tmp_imgs = list_files(location = "./", pattern = img_pattern)
        if len(tmp_imgs) > 0:
            for f in tmp_imgs:
                os.remove(f)
            return 0
        return 

    def close_workbook(self):
        '''
        Finish writing the contents of the workbook and close the file.
        '''
        self.workbook.close()
        self.remove_tmp_img(img_pattern = r".tmp_image_[0-9]+.png")
        logging.info("All temp images have been removed.")

to_cell_range_text 

to_cell_range_text(first_row, first_col, last_row, last_col)

To Excel Cell Range.

源代码位于： ExcelMaster/ExcelMaster.py 
23
24
25
def to_cell_range_text(self, first_row, first_col, last_row, last_col):
    """ To Excel Cell Range. """
    return xl_range(first_row, first_col, last_row, last_col)

cell_range_to_loc 

cell_range_to_loc(cell_range_text)

Convert text cell range expression to a list of values.

源代码位于： ExcelMaster/ExcelMaster.py 
27
28
29
30
31
32
33
def cell_range_to_loc(self, cell_range_text):
    """ Convert text cell range expression to a list of values. """
    cell_range_list = cell_range_text.split(":")
    res = []
    for x in cell_range_list:
        res += list(xl_cell_to_rowcol(x))
    return res

colletter_to_textloc 

colletter_to_textloc(row_index, col_letter)

Append Row Index to the given Column Letter-Formatted Index.

源代码位于： ExcelMaster/ExcelMaster.py 
35
36
37
38
39
40
def colletter_to_textloc(self, row_index, col_letter):
    """ Append Row Index to the given Column Letter-Formatted Index. """
    col_letter = col_letter if ":" in col_letter else (col_letter + ":" + col_letter)
    output = col_letter.split(":")
    output = ":".join([col + str(row_index) for col in output])
    return output

set_color_scale 

set_color_scale(worksheet, cell_range, colors=('#F8696B', '#FFEB84', '#63BE7B'))

Set Color Scale.

源代码位于： ExcelMaster/ExcelMaster.py 
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
def set_color_scale(self, worksheet, cell_range,
                    colors = ("#F8696B", "#FFEB84", "#63BE7B")):
    """ Set Color Scale. """
    if len(colors) == 3:
        f = {
                "type": "3_color_scale",
                "min_color": colors[0],
                "mid_color": colors[1],
                "max_color": colors[2],
            }
    elif len(colors) == 2:
        f = {
                "type": "2_color_scale",
                "min_color": colors[0],
                "max_color": colors[1],
            }
    else:
        raise ValueError("Please give 2 or 3 colors!")

    if isinstance(cell_range, list) or isinstance(cell_range, tuple):
        cell_range = self.to_cell_range_text(*cell_range)

    worksheet.conditional_format(cell_range, f)
    return 0

set_data_bar 

set_data_bar(worksheet, cell_range, bar_color='#63C384')

Set Data Bar in a Worksheet for a range of cells.

源代码位于： ExcelMaster/ExcelMaster.py 
67
68
69
70
71
72
73
74
75
76
77
78
def set_data_bar(self, worksheet, cell_range, bar_color = "#63C384"):
    """ Set Data Bar in a Worksheet for a range of cells. """

    f = {'type': 'data_bar',
         'data_bar_2010': True,
         "bar_color": bar_color}

    if isinstance(cell_range, list) or isinstance(cell_range, tuple):
        cell_range = self.to_cell_range_text(*cell_range)

    worksheet.conditional_format(cell_range, f)
    return 0

set_cell_format 

set_cell_format(worksheet, cell_range, cformat, cell_condition=None)

Set format for a range of cell.

源代码位于： ExcelMaster/ExcelMaster.py 
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
def set_cell_format(self, worksheet, cell_range, cformat, cell_condition = None):
    """ Set format for a range of cell. """

    if cell_condition and isinstance(cell_condition, tuple):
        criteria = cell_condition[0].lower()
        value = cell_condition[1]

    if isinstance(cell_range, list) or isinstance(cell_range, tuple):
        cell_range = self.to_cell_range_text(*cell_range)

    if isinstance(cformat, str):
        cformat = self.dict_cell_format[cformat]

    if cell_condition and isinstance(cell_condition, tuple):

        if (criteria == 'between') or (criteria == 'not between'):
            worksheet.conditional_format(cell_range, {"type": "cell", 
                                                      "criteria": criteria, 
                                                      "minimum": value[0],
                                                      "maximum": value[1], 
                                                      "format": cformat})

            return 0

        worksheet.conditional_format(cell_range, {"type": "cell", 
                                                  "criteria": criteria, 
                                                  "value": value, 
                                                  "format": cformat})
        return 0

    worksheet.conditional_format(cell_range, {'type': 'no_errors', "format": cformat}) 
    return 0

set_cell_format_rbyr 

set_cell_format_rbyr(worksheet, start_row, condition_list, condition, ifelse_col, cformat='YELLOW_BG')

Conditionally Highlight Cells Row by Row.

源代码位于： ExcelMaster/ExcelMaster.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
def set_cell_format_rbyr(self, worksheet, start_row, condition_list, condition, ifelse_col, cformat = "YELLOW_BG"):
    """ Conditionally Highlight Cells Row by Row. """

    if_col = ifelse_col[0]
    else_col = ifelse_col[1]

    i = 0
    row_concur = start_row
    while i < len(condition_list):
        target = condition_list[i]

        if val_input_condition(target, condition):
            if if_col:
                self.set_cell_format(worksheet, 
                                   cell_range=self.colletter_to_textloc(row_concur + 1, if_col), 
                                   cformat=cformat)

        else:
            if else_col:
                self.set_cell_format(worksheet, 
                                   cell_range=self.colletter_to_textloc(row_concur + 1, else_col), 
                                   cformat=cformat)

        i += 1
        row_concur = row_concur + 1
    return 0

remove_tmp_img 

remove_tmp_img(img_pattern='.tmp_image_[0-9]+.png')

Remove Temp Images.

源代码位于： ExcelMaster/ExcelMaster.py 
140
141
142
143
144
145
146
147
def remove_tmp_img(self, img_pattern = r".tmp_image_[0-9]+.png"):
    """ Remove Temp Images. """
    tmp_imgs = list_files(location = "./", pattern = img_pattern)
    if len(tmp_imgs) > 0:
        for f in tmp_imgs:
            os.remove(f)
        return 0
    return

close_workbook 

close_workbook()

Finish writing the contents of the workbook and close the file.

源代码位于： ExcelMaster/ExcelMaster.py 
149
150
151
152
153
154
155
def close_workbook(self):
    '''
    Finish writing the contents of the workbook and close the file.
    '''
    self.workbook.close()
    self.remove_tmp_img(img_pattern = r".tmp_image_[0-9]+.png")
    logging.info("All temp images have been removed.")

ExcelMaster

Bases: ExcelWorkbook

Write anything to Excel (Worksheet-level Operator)

源代码位于： ExcelMaster/ExcelMaster.py 
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
class ExcelMaster(ExcelWorkbook):
    """  Write anything to Excel (Worksheet-level Operator) """
    def __init__(self, filepath, verbose, gap_number = 2, init_loc = (0, 0)):
        super().__init__(filepath, verbose)
        self.curr_row = init_loc[0]
        self.curr_col = init_loc[1]
        self.gap_number = gap_number + 1

        self.default_row_height = 20
        self.default_col_width = 64

        self.max_nrows = 1048576
        self.max_ncols = 16384

    def add_worksheet(self, name, hide_grid = True, reset_loc = True, cell_scale = True, auto_fit = False, zoom_perc = 100, tab_color = None):
        """ Add a worksheet. """
        ws = self.workbook.add_worksheet(name)

        if hide_grid:
            ws.hide_gridlines(2)

        if reset_loc:
            self.reset_curr_loc()

        if isinstance(cell_scale, tuple):
            self.set_cell_size(ws, cell_scale)
        if cell_scale is True:
            self.set_cell_size(ws)

        if auto_fit:
            ws.auto_fit()

        if tab_color:
            ws.set_tab_color(tab_color)

        ws.set_zoom(zoom_perc)
        self.ws_dict[name] = ws
        self.engine.sheets[name] = ws
        return ws

    def reset_curr_loc(self, loc = (0, 0)):
        """ Reset Current Location. """

        self.curr_row = loc[0]
        self.curr_col = loc[1]
        return 0

    def _reset_cell_size(self):
        """ Reset Cell Size to Default Value. """
        self.default_row_height = 20
        self.default_col_width = 64
        return 0

    def set_cell_size(self, worksheet, size_scale = (1, 1)):
        """ Set Cell Size in Scale. """

        if isinstance(size_scale, tuple) and len(size_scale) == 2:
            self._reset_cell_size()
            self.default_row_height = self.default_row_height * size_scale[0]
            self.default_col_width =  self.default_col_width * size_scale[1]

        for i in range(0, self.max_nrows):
            worksheet.set_row_pixels(i, height=self.default_row_height)

        worksheet.set_column_pixels(0, self.max_ncols - 1, width=self.default_col_width)
        return 0

    def get_curr_loc(self, toCell = False):
        """ Get Current Location in worksheet. """
        if toCell:
            return xl_rowcol_to_cell(self.curr_row, self.curr_col)
        return (self.curr_row, self.curr_col)

    def set_border_line(self, worksheet, valuerange, border_line = 1):
        """ Set border line for a range of cells. """
        border_fmt = self.workbook.add_format({'bottom': border_line, 'top': border_line, 'left': border_line, 'right': border_line})
        self.set_cell_format(worksheet = worksheet, cell_range = valuerange, cformat = border_fmt)
        return 0

    def merge_col(self, worksheet, loc = None, nrows = 1, ncols = 1, text = "", skipby = 'row', cformat = 'BLUE_H4', retCellRange = None):
        """ Merge columns in a single row. """

        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col
        written_range = [start_row, start_col, start_row + nrows - 1, start_col + ncols - 1]

        worksheet.merge_range(*written_range, text, self.dict_cell_format[cformat])

        if self.verbose:
            logging.info(f"Merged Cells: {self.to_cell_range_text(*written_range)}")

        # Skipped by Rows/Columns
        if skipby == 'row':
            self.curr_row = (start_row + nrows + self.gap_number)
        if skipby == 'col':
            self.curr_col = (start_col + ncols + self.gap_number)

        # Return written location by Cell Text/Value Range
        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        return 0

    def write_dataframe(self, worksheet, df, loc = None, title = None, index = False, header = True, skipby = 'row', titleformat = "BLUE_H4", headerformat = "TABLE_HEADER", valueformat="----", retCellRange = None):
        """ Write a dataframe to excel file. """

        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col

        ncols = df.shape[1] 
        nrows = df.shape[0]

        ## Get Number of Index Columns
        index_ncols = 0
        if index:
            index_ncols = len(df.index.names)
            ncols += index_ncols

        ## Get Number of Header Rows
        header_nrows = 0
        if header:
            header_nrows = len(df.columns.names)
            nrows += header_nrows

        ## Get Number of Title Rows
        title_nrows = 0
        if title:
            title_nrows = 1
            nrows += title_nrows

        ## Get Header Range (Include Index)
        if header:
            header_start_row = (start_row + title_nrows)
            header_start_col = start_col
            header_end_row = max((start_row + header_nrows - 1), header_start_row)
            header_end_col = (start_col + ncols - 1)
            header_range = self.to_cell_range_text(header_start_row, header_start_col, 
                                                   header_end_row, header_end_col)

        ## Write DataFrame
        if title:
            self.merge_col(worksheet = worksheet, loc = loc, ncols = ncols, cformat=titleformat, 
                           text = title, skipby = None)
            df.to_excel(self.engine, sheet_name = worksheet.name, startrow = start_row + title_nrows, 
                        startcol = start_col, header = header, index = index)
        else:
            df.to_excel(self.engine, sheet_name = worksheet.name, startrow = start_row, 
                        startcol = start_col, header = header, index = index)


        ## Get Value Range (Include Index)
        value_start_row = (start_row + title_nrows + header_nrows)
        value_start_col = start_col
        value_end_row = (start_row + nrows - 1)
        value_end_col = (start_col + ncols - 1)
        value_range = [value_start_row, value_start_col, value_end_row, value_end_col]

        ## Set Format
        self.set_cell_format(worksheet = worksheet, cell_range = value_range, cformat = valueformat)
        if header:
            self.set_cell_format(worksheet = worksheet, cell_range = header_range, cformat = headerformat)

        written_range = [start_row, start_col, (start_row + nrows - 1), (start_col + ncols - 1)]

        if self.verbose:
            logging.info(f"Table Written in Cell Range: {self.to_cell_range_text(*written_range)}")

        if skipby == 'row':
            self.curr_row = (start_row + nrows + self.gap_number)
        if skipby == 'col':
            self.curr_col = (start_col + ncols + self.gap_number)

        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        return 0

    def _get_image_size(self, figPath, figScale = (1, 1), retSizeInCell = True):
        """ Get Image Size in Excel Cells. """
        img = Image.open(figPath)
        w, h = img.size
        (width, height) = (img.width * figScale[0], img.height * figScale[1])
        h_in_cell = np.floor(height/self.default_row_height)
        w_in_cell = np.ceil(width/self.default_col_width)
        img.close()
        if retSizeInCell:
            return (w_in_cell, h_in_cell)
        return (width, height)

    def _resize_image(self, imgPath, resize, outPath, size_in_cell = True):
        """ Resize image. """
        # Open the image
        image = Image.open(imgPath)
        new_image = image.resize((resize[0], resize[1]))
        if size_in_cell:
            # Resize the image
            new_image = image.resize((resize[1] * self.default_col_width, resize[0] * self.default_row_height))
        # Save the resized image
        new_image.save(outPath)
        image.close()
        return 0

    def insert_image(self, worksheet, figPath, figScale = (1, 1), loc = None, skipby = 'row', retCellRange = None):
        """ Insert an image to the sheet. """
        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col

        start_cell = xl_rowcol_to_cell(start_row, start_col)
        figsize_in_cells = self._get_image_size(figPath = figPath, figScale = figScale, retSizeInCell = True)

        worksheet.insert_image(start_cell, figPath, {"x_scale": figScale[0], "y_scale": figScale[1]})

        # Skipped by Rows/Columns
        if skipby == 'row':
            self.curr_row = (start_row + int(figsize_in_cells[1]) + self.gap_number)
        if skipby == 'col':
            self.curr_col = (start_col + int(figsize_in_cells[0]) + self.gap_number)

        written_range = [start_row, start_col, 
                         start_row + int(figsize_in_cells[1]), 
                         start_col + int(figsize_in_cells[0])]

        # Return written location by Cell Text/Value Range
        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        if self.verbose:
            logging.info(f"Image Written in Cell Range: {self.to_cell_range_text(*written_range)}")

        return 0

    def __add_chart_data_tab(self, tabname, hide = True, max_num = 99999):
        """ Add a temp tab for chart data. """
        i = 0
        while i <= max_num:
            tabname_i = (tabname + str(i))
            if tabname_i not in self.ws_dict:
                ws = self.add_worksheet(tabname_i, reset_loc = False, 
                                        cell_scale = None, 
                                        auto_fit = False, 
                                        zoom_perc = 100)
                ws.hide()
                return ws
            i += 1
        return -1

    def _transpose_df_for_chart(self, df, y_list, x = None):
        """ Transpose Dataframe for Chart Structrue. """

        _df = df.copy()
        _df.columns.name = None
        _df.index.name = None

        if x is None:
            _df = _df[y_list].T
            _df = _df.reset_index(drop=False)
        else:
            x = x if isinstance(x, list) else [x]
            _df = tanspose_dataframe(_df[[*x, *y_list]], x)

        _df.columns.name = None
        _df.index.name = None
        return _df

    def __convert_to_none_tuple(self, x = None):
        """ Convert None Type to Tuple of Nones. """
        if x is None:
            return (None, None)
        return x

    def __validate_input_chart_obj(self, chart_type, input_chart):
        """ Validate if the given append_to_chart object is aligned with chart_type argument. """

        if chart_type == "line":
            return isinstance(input_chart, xlsxwriter.chart_line.ChartLine)
        if chart_type in ["column", "stacked_column"]:
            return isinstance(input_chart, xlsxwriter.chart_column.ChartColumn)
        if chart_type == "pie":
            return isinstance(input_chart, xlsxwriter.chart_pie.ChartPie)

    def write_chart(self, worksheet, df, y_list, x = None, title = "", 
                    chart_size = (30, 13), chart_type = "line",
                    y_axis_range = (None, None), y_num_format = None,
                    y2_axis = False, loc = None, retChart = False, 
                    skipby = "row", outputData = False, retCellRange = None,
                    xy_axes_name = ("", ""), major_gridlines = False,
                    legend = "bottom", line_marker = "circle", line_type = "solid", 
                    chart_style = None, append_to_chart = None): 
        """ Write line chart to Excel worksheet."""

        if isinstance(chart_type, str):
            if chart_type == "line":
                chart_type = {'type': 'line'}
            elif chart_type == "column":
                chart_type = {'type': 'column'}
            elif chart_type == "stacked_column":
                chart_type = {'type': 'column', "subtype": "stacked"}
            elif chart_type == "pie":
                chart_type = {"type": "pie"}
            else:
                raise ValueError(" Please select one from 'line', 'column', 'stacked_column' or 'pie'. ")

        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col

        y_axis_range = self.__convert_to_none_tuple(y_axis_range)

        df_t = self._transpose_df_for_chart(df = df, y_list = y_list, x = x)
        if x is None:
            x = list(df.index.names)
        if isinstance(x, str):
            x = [x]
        y = "index" if len(x) == 1 else tuple(["index"] + [''] * (len(x) - 1))
        x_list = [x for x in df_t.columns if x != y]

        data_nrows = df_t.shape[0]
        data_ncols = df_t.shape[1]

        raw_data_ws = self.__add_chart_data_tab("__CHRT_DATA_")

        ## if y not given, then use index value as y series.
        data_index_as_y = True
        if y is None:
            sel_df = df_t[[*x_list]]
        else:
            sel_df = df_t[[y, *x_list]]
            sel_df = sel_df.set_index(y)
            sel_df.index.name = None

        ## if output chart data to current worksheet.
        if outputData:
            raw_data_ws = worksheet
            df_range = self.write_dataframe(worksheet = raw_data_ws, df = sel_df, index = data_index_as_y, title = None, skipby=None, retCellRange="value", loc = (start_row, start_col))
            chart_loc = (df_range[2] + self.gap_number, df_range[1])
        else:
            df_range = self.write_dataframe(worksheet = raw_data_ws, df = sel_df, index = data_index_as_y, title = None, skipby=None, retCellRange="value", loc = (0,0))
            chart_loc = (start_row, start_col)

        x_count = len(x_list)
        nrows = df_t.shape[0]

        data_row_anchor = df_range[0]
        data_col_anchor = df_range[1]
        row_shift = 0

        category_range = [df_range[0], df_range[1] + 1, 
                          df_range[0] + (len(x) - 1), df_range[3]]

        if self.verbose:
            logging.info(f"Category Cell Range: {self.to_cell_range_text(*category_range)}")

        chart = self.workbook.add_chart(chart_type)
        if append_to_chart is not None:
            if self.__validate_input_chart_obj(chart_type = chart_type["type"], input_chart = append_to_chart):
                chart = append_to_chart
            else:
                warnings.warn("WARNING: Can only append data to the chart that has the same chart type as your given one.")

        value_start = len(x) + 1 if len(x) > 1 else len(x)
        for row_shift in range(value_start, value_start + nrows, 1):

            value_range = [data_row_anchor + row_shift, data_col_anchor + 1, 
                           data_row_anchor + row_shift, data_col_anchor + x_count]

            chart.add_series({
                'name':        [raw_data_ws.name, (data_row_anchor + row_shift), data_col_anchor],
                'categories':  [raw_data_ws.name, *category_range],
                'values':      [raw_data_ws.name, *value_range],
                'marker':      {'type': line_marker},
                "line" :       {'dash_type': line_type},
                'data_labels': {'percentage': True} if chart_type['type'] == 'pie' else None,
                'y2_axis':     y2_axis,
            })
            if self.verbose:
                logging.info("Values Cell Range: %s", self.to_cell_range_text(*value_range))

        chart.set_title({'name': title})
        chart.set_legend({'position': str(legend)})
        chart.set_size({"height": chart_size[0] * self.default_row_height, # by row 15
                        "width": chart_size[1] * self.default_col_width}) # by col 8.43

        chart.set_x_axis({"name": xy_axes_name[0]})

        set_y_axis_dict = {"name": xy_axes_name[1], 
                           "major_gridlines": {"visible": int(major_gridlines)},
                           'min': y_axis_range[0], 
                           'max': y_axis_range[1],
                           'num_format': y_num_format}
        if y2_axis:
            chart.set_y2_axis(set_y_axis_dict)
        else:
            chart.set_y_axis(set_y_axis_dict)

        # Setting Chart Style
        if chart_style:
            chart.set_style(chart_style)

        # Need to Return Chart before Insert it to the worksheet.
        if retChart:
            return chart

        worksheet.insert_chart(
            chart_loc[0], 
            chart_loc[1], 
            chart
        )

        written_range = [start_row, start_col, int(chart_loc[0] + chart_size[0]), int(chart_loc[1] + chart_size[1])]
        if outputData:

            written_range = [start_row, start_col, 
                             (start_row + data_nrows + self.gap_number + chart_size[0]),
                             max(df_range[3], start_col + chart_size[1])]

        if skipby == 'row':
            if outputData:
                self.curr_row = (start_row + data_nrows + self.gap_number + chart_size[0] + self.gap_number - 1)
            else:
                self.curr_row = (start_row + chart_size[0] + self.gap_number - 1)
        if skipby == 'col':
            self.curr_col = (start_col + int(chart_size[1]) + self.gap_number)

        if self.verbose:
            logging.info(f"Chart Written in Cell Range: {self.to_cell_range_text(*written_range)}")

        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        return 0

    def write_combined_chart(self, worksheet, chart1, chart2, 
                             loc = None, chart_size = (30, 13), 
                             skipby = "row", retCellRange = None):
        """ Combined two chart objects and then write to Excel worksheet. """

        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col

        chart1.combine(chart2)
        worksheet.insert_chart(xl_rowcol_to_cell(start_row, start_col), chart1)

        written_range = [start_row, start_col, (start_row + chart_size[0]), (start_col + chart_size[1])]

        if skipby == 'row':
            self.curr_row = (start_row + chart_size[0] + self.gap_number - 1)
        if skipby == 'col':
            self.curr_col = (start_col + chart_size[1] + self.gap_number)

        if self.verbose:
            logging.info(f"Chart Written in Cell Range: {self.to_cell_range_text(*written_range)}")

        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        return 0


    def write_duo_chart(self, worksheet, df,
                        y1_list, y2_list = None, x = None,
                        c1_type = "column", c2_type = "line", 
                        y1_axis_range = (0, 1), y2_axis_range = None,
                        y1_num_format = None, y2_num_format = None,
                        y1_line_marker = "circle", y2_line_marker = "circle",
                        y1_line_type = "solid", y2_line_type = "solid",
                        loc = None, title = "", chart_size = (30, 13),
                        xy_axes_name = ("", ""), major_gridlines = False,
                        retChart = False, retCellRange = None,
                        skipby = "row"):
        """ Write duo-chart sharing the same x axis. """

        start_row = loc[0] if loc else self.curr_row
        start_col = loc[1] if loc else self.curr_col

        y2_axis = True
        if y2_list is None:
            y2_axis = False

        if y2_axis_range is None:
            y2_axis_range = y1_axis_range

        xy_name = (xy_axes_name[0], xy_axes_name[1])
        xy2_name = (xy_axes_name[0], xy_axes_name[1])
        if y2_axis and len(xy_axes_name) >= 3:
            xy_name = (xy_axes_name[0], xy_axes_name[1])
            xy2_name = (xy_axes_name[0], xy_axes_name[2])
        if y2_axis and len(xy_axes_name) < 3:
            xy_name = (xy_axes_name[0], xy_axes_name[1])
            xy2_name = (xy_axes_name[0], "")

        chart1 = self.write_chart(df = df, 
                                  x = x, 
                                  y_list = y1_list, 
                                  worksheet = worksheet, 
                                  title = title,
                                  chart_type = c1_type, 
                                  chart_size = chart_size,
                                  y_axis_range = y1_axis_range,
                                  xy_axes_name = xy_name,
                                  major_gridlines = major_gridlines,
                                  y_num_format = y1_num_format,
                                  line_type = y1_line_type,
                                  line_marker = y1_line_marker,
                                  retChart = True)

        chart2 = self.write_chart(df = df, 
                                  x = x,
                                  y_list = y2_list, 
                                  worksheet=worksheet, 
                                  title = title, 
                                  chart_type = c2_type, 
                                  chart_size = chart_size,
                                  y_axis_range = y2_axis_range,
                                  y2_axis = y2_axis,
                                  xy_axes_name = xy2_name,
                                  major_gridlines = False,
                                  y_num_format = y2_num_format,
                                  line_type = y2_line_type,
                                  line_marker = y2_line_marker,
                                  retChart=True)

        # Need to Return Chart before Insert it to the worksheet.
        if retChart:
            return (chart1, chart2)

        cell_range = self.write_combined_chart(worksheet, 
                                  chart1, chart2, 
                                  loc = loc, chart_size = chart_size, 
                                  skipby = skipby, retCellRange = retCellRange)

        return cell_range

    def write_text_by_dict(self, worksheet, dict_cells):
        """ Write text using Python dictionary. """
        for cell in dict_cells:
            list_contents = dict_cells[cell]

            if ':' in cell:
                text, cell_format = list_contents
                worksheet.merge_range(cell, text, self.dict_cell_format[cell_format])

            else:
                if len(list_contents) == 1:
                    list_items = []

                    # Text formats begin with '~~~'
                    list_mixed_items = list_contents[0]
                    for item in list_mixed_items:
                        if item.startswith('~~~'):
                            cell_format = item.split('~~~')[1]
                            item = self.dict_cell_format[cell_format]

                            list_items.append(item)
                        else:
                            list_items.append(item)

                    worksheet.write_rich_string(cell, *list_items)

                else:
                    text, cell_format = list_contents
                    worksheet.write(cell, text, self.dict_cell_format[cell_format])

    def __split_line_by_format_sign(self, line):
        """ To split line by specified format sign '{}'. """

        ## find all format sign '{}'
        format_sign = re.findall(".*?{(.*?)}.*?", line)
        format_sign = format_sign if len(format_sign) != 0 else ['']
        format_sign = [x.lstrip().rstrip() for x in format_sign]

        ## find all cell formats
        cell_format_sign = re.findall(".*?\[\[(.*?)\]\]$", line.strip().replace("\n", ""))
        cell_format_sign = [x.lstrip().rstrip() for x in cell_format_sign]

        ## clean up text by removing cell format express
        if len(cell_format_sign) > 0:
            line = line.split("[[")[0]

        ## find text before the first format sign appeared.
        text_bf_curly = re.findall(r"(.*?)\{", line)
        text_bf_curly = [text_bf_curly[0]] if len(text_bf_curly) != 0 else ['']
        text_bf_curly = [x.strip("\n") for x in text_bf_curly]

        ## find text after the first format sign appeared.
        text_af_curly = re.findall(r"\}\s*(.*?)(?=\s*\{|$)", line) if re.search(".*?{(.*?)}.*?", line) else [line]
        text_af_curly = [x.strip("\n") for x in text_af_curly]

        return text_bf_curly, format_sign, text_af_curly, cell_format_sign

    def __parse_line_by_format_sign(self, worksheet, loc, line):
        """ Parse text by format sign. """

        text_bf_curly, format_sign, text_af_curly, cell_format_sign = self.__split_line_by_format_sign(line)

        start_text = text_bf_curly[0]
        # if len(start_text) > 0 or len(format_sign) >= 2:
        if len(format_sign) >= 2:
            # if one line has more than 2 formats specified.

            res = [loc, start_text] if start_text != '' else [loc]
            assert len(format_sign) == len(text_af_curly)

            for fmt, s2 in zip(format_sign, text_af_curly):
                res.append(self.dict_cell_format[fmt] if fmt else self.dict_cell_format[""])
                res.append(s2.strip('\n')) # remove enter sign

            # Write line by line
            if self.verbose:
                logging.info(res)

            worksheet.write_rich_string(*res)

        if len(format_sign) < 2:
            # if one line has more than 2 formats specified.

            res = [loc, start_text] if start_text != '' else [loc]
            assert len(format_sign) == len(text_af_curly)

            fmt = format_sign[0]
            text = text_af_curly[0].strip("\n")
            res.append(text)
            res.append(self.dict_cell_format[fmt])

            # Write line by line
            if self.verbose:
                logging.info(res)

            worksheet.write_string(*res)

        if len(cell_format_sign) > 0:
            self.set_cell_format(worksheet = worksheet, cell_range = loc, cformat = cell_format_sign[0])
        return 0

    def write_text_content(self, worksheet, input_text = None, txt_path = None, loc = None, retCellRange = None):
        """ Write text content line by line to the worksheet. """

        row_anchor = loc[0] if loc else self.curr_row
        col_anchor = loc[1] if loc else self.curr_col

        start_row = row_anchor
        start_col = col_anchor

        if (input_text) and (txt_path):
            raise ValueError("Please give either input_text or txt_path, not both !!!")

        if (input_text is None) and (txt_path is None):
            raise ValueError("Please specify either input_text or txt_path.")

        if txt_path is not None:
            file_notes = open(txt_path, 'r')
            textlines = file_notes.readlines()

        if input_text is not None:
            textlines = input_text.split("\n")

        for line in textlines:
            # Write text line by line
            loc = xl_rowcol_to_cell(row_anchor, col_anchor)

            if " [>] " in line:
                line_split = line.split(" [>] ")
                col_shift = 0
                for sub_line in line_split:
                    sub_line = sub_line.rstrip()
                    self.__parse_line_by_format_sign(worksheet = worksheet, loc = loc, line = sub_line)
                    col_shift += 1
                    loc = xl_rowcol_to_cell(row_anchor, col_anchor + col_shift)
            else:
                self.__parse_line_by_format_sign(worksheet = worksheet, loc = loc, line = line)

            row_anchor += 1

        self.curr_row = (row_anchor - 1)

        end_row = row_anchor
        end_col = col_anchor

        written_range = [start_row, start_col, end_row, end_col]

        if self.verbose:
            logging.info(f"Text Written in Cell Range: {self.to_cell_range_text(*written_range)}")

        if retCellRange == "text":
            return self.to_cell_range_text(*written_range)
        if retCellRange == "value":
            return written_range

        return 0

    @staticmethod
    def plot_boxplot(df, x, y, y_percentage = False, colored_box = True, color_grp = (10, 1), title = "", fontsize = 14, figsize = (8, 6), show_fig = True, img_path = None, transp_bg = False):
        """ Plot Box Plot Chart using matplotlib. """

        plt.style.use('default')

        fig, ax = plt.subplots(1, 1, figsize = figsize, dpi=200)

        box_plot_data = convert_to_boxplot_data(df, x, y, True)

        bplot = ax.boxplot(box_plot_data.values(), patch_artist=colored_box, widths = 0.4)
        ax.set_xticklabels(box_plot_data.keys(), fontsize = fontsize)
        ax.set_ylabel(string_proc(y), color='black', fontsize = fontsize)
        ax.set_xlabel(string_proc(x), color='black', fontsize = fontsize)
        ax.tick_params(axis='both', labelsize=fontsize)
        ax.grid(True, 'major', 'y', ls='--', lw=.5, c='k', alpha=.3)
        ax.set_title(title, fontsize=fontsize + 4)

        if colored_box:
            colors = color_input_validation(color_grp, len(box_plot_data.keys()))
            for patch, color in zip(bplot['boxes'], colors):
                patch.set_facecolor(color)
                patch.set_alpha(.7)

        if y_percentage:
            plt.gca().yaxis.set_major_formatter(PercentFormatter(100)) 
        plt.tight_layout()

        if show_fig:
            plt.show()

        if img_path:
            fig.savefig(img_path, transparent = transp_bg, dpi=200)

        plt.close()
        return fig, ax

    def write_boxplot(self, ws, df, x, y, y_percentage = False, colored_box = True, color_grp = (10, 1), title = "", 
                      fontsize = 14, figsize = (30, 13), show_fig = False, img_path = None, transp_bg = False,
                      loc = None, skipby = "row", retCellRange = None):
        """ Write boxplot to Worksheet. """

        currTime = getCurrentDateTime()
        rn = str(random.randrange(0, 1000))
        rn_num = currTime + rn
        tmp_image_path = f"./.tmp_image_{rn_num}.png"

        ExcelMaster.plot_boxplot(df = df, 
                                 x = x, y = y, 
                                 y_percentage = y_percentage, 
                                 colored_box = colored_box, 
                                 color_grp = color_grp, 
                                 title = title, 
                                 fontsize = fontsize, 
                                 show_fig = show_fig, 
                                 transp_bg = transp_bg,
                                 img_path = tmp_image_path)

        self._resize_image(tmp_image_path, figsize, tmp_image_path)
        ret_range = self.insert_image(ws, figPath=tmp_image_path, figScale=(1, 1), loc = loc, skipby = skipby, retCellRange = retCellRange)

        return ret_range

add_worksheet 

add_worksheet(name, hide_grid=True, reset_loc=True, cell_scale=True, auto_fit=False, zoom_perc=100, tab_color=None)

Add a worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
def add_worksheet(self, name, hide_grid = True, reset_loc = True, cell_scale = True, auto_fit = False, zoom_perc = 100, tab_color = None):
    """ Add a worksheet. """
    ws = self.workbook.add_worksheet(name)

    if hide_grid:
        ws.hide_gridlines(2)

    if reset_loc:
        self.reset_curr_loc()

    if isinstance(cell_scale, tuple):
        self.set_cell_size(ws, cell_scale)
    if cell_scale is True:
        self.set_cell_size(ws)

    if auto_fit:
        ws.auto_fit()

    if tab_color:
        ws.set_tab_color(tab_color)

    ws.set_zoom(zoom_perc)
    self.ws_dict[name] = ws
    self.engine.sheets[name] = ws
    return ws

reset_curr_loc 

reset_curr_loc(loc=(0, 0))

Reset Current Location.

源代码位于： ExcelMaster/ExcelMaster.py 
198
199
200
201
202
203
def reset_curr_loc(self, loc = (0, 0)):
    """ Reset Current Location. """

    self.curr_row = loc[0]
    self.curr_col = loc[1]
    return 0

set_cell_size 

set_cell_size(worksheet, size_scale=(1, 1))

Set Cell Size in Scale.

源代码位于： ExcelMaster/ExcelMaster.py 
211
212
213
214
215
216
217
218
219
220
221
222
223
def set_cell_size(self, worksheet, size_scale = (1, 1)):
    """ Set Cell Size in Scale. """

    if isinstance(size_scale, tuple) and len(size_scale) == 2:
        self._reset_cell_size()
        self.default_row_height = self.default_row_height * size_scale[0]
        self.default_col_width =  self.default_col_width * size_scale[1]

    for i in range(0, self.max_nrows):
        worksheet.set_row_pixels(i, height=self.default_row_height)

    worksheet.set_column_pixels(0, self.max_ncols - 1, width=self.default_col_width)
    return 0

get_curr_loc 

get_curr_loc(toCell=False)

Get Current Location in worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
225
226
227
228
229
def get_curr_loc(self, toCell = False):
    """ Get Current Location in worksheet. """
    if toCell:
        return xl_rowcol_to_cell(self.curr_row, self.curr_col)
    return (self.curr_row, self.curr_col)

set_border_line 

set_border_line(worksheet, valuerange, border_line=1)

Set border line for a range of cells.

源代码位于： ExcelMaster/ExcelMaster.py 
231
232
233
234
235
def set_border_line(self, worksheet, valuerange, border_line = 1):
    """ Set border line for a range of cells. """
    border_fmt = self.workbook.add_format({'bottom': border_line, 'top': border_line, 'left': border_line, 'right': border_line})
    self.set_cell_format(worksheet = worksheet, cell_range = valuerange, cformat = border_fmt)
    return 0

merge_col 

merge_col(worksheet, loc=None, nrows=1, ncols=1, text='', skipby='row', cformat='BLUE_H4', retCellRange=None)

Merge columns in a single row.

源代码位于： ExcelMaster/ExcelMaster.py 
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
def merge_col(self, worksheet, loc = None, nrows = 1, ncols = 1, text = "", skipby = 'row', cformat = 'BLUE_H4', retCellRange = None):
    """ Merge columns in a single row. """

    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col
    written_range = [start_row, start_col, start_row + nrows - 1, start_col + ncols - 1]

    worksheet.merge_range(*written_range, text, self.dict_cell_format[cformat])

    if self.verbose:
        logging.info(f"Merged Cells: {self.to_cell_range_text(*written_range)}")

    # Skipped by Rows/Columns
    if skipby == 'row':
        self.curr_row = (start_row + nrows + self.gap_number)
    if skipby == 'col':
        self.curr_col = (start_col + ncols + self.gap_number)

    # Return written location by Cell Text/Value Range
    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    return 0

write_dataframe 

write_dataframe(worksheet, df, loc=None, title=None, index=False, header=True, skipby='row', titleformat='BLUE_H4', headerformat='TABLE_HEADER', valueformat='----', retCellRange=None)

Write a dataframe to excel file.

源代码位于： ExcelMaster/ExcelMaster.py 
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
def write_dataframe(self, worksheet, df, loc = None, title = None, index = False, header = True, skipby = 'row', titleformat = "BLUE_H4", headerformat = "TABLE_HEADER", valueformat="----", retCellRange = None):
    """ Write a dataframe to excel file. """

    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col

    ncols = df.shape[1] 
    nrows = df.shape[0]

    ## Get Number of Index Columns
    index_ncols = 0
    if index:
        index_ncols = len(df.index.names)
        ncols += index_ncols

    ## Get Number of Header Rows
    header_nrows = 0
    if header:
        header_nrows = len(df.columns.names)
        nrows += header_nrows

    ## Get Number of Title Rows
    title_nrows = 0
    if title:
        title_nrows = 1
        nrows += title_nrows

    ## Get Header Range (Include Index)
    if header:
        header_start_row = (start_row + title_nrows)
        header_start_col = start_col
        header_end_row = max((start_row + header_nrows - 1), header_start_row)
        header_end_col = (start_col + ncols - 1)
        header_range = self.to_cell_range_text(header_start_row, header_start_col, 
                                               header_end_row, header_end_col)

    ## Write DataFrame
    if title:
        self.merge_col(worksheet = worksheet, loc = loc, ncols = ncols, cformat=titleformat, 
                       text = title, skipby = None)
        df.to_excel(self.engine, sheet_name = worksheet.name, startrow = start_row + title_nrows, 
                    startcol = start_col, header = header, index = index)
    else:
        df.to_excel(self.engine, sheet_name = worksheet.name, startrow = start_row, 
                    startcol = start_col, header = header, index = index)


    ## Get Value Range (Include Index)
    value_start_row = (start_row + title_nrows + header_nrows)
    value_start_col = start_col
    value_end_row = (start_row + nrows - 1)
    value_end_col = (start_col + ncols - 1)
    value_range = [value_start_row, value_start_col, value_end_row, value_end_col]

    ## Set Format
    self.set_cell_format(worksheet = worksheet, cell_range = value_range, cformat = valueformat)
    if header:
        self.set_cell_format(worksheet = worksheet, cell_range = header_range, cformat = headerformat)

    written_range = [start_row, start_col, (start_row + nrows - 1), (start_col + ncols - 1)]

    if self.verbose:
        logging.info(f"Table Written in Cell Range: {self.to_cell_range_text(*written_range)}")

    if skipby == 'row':
        self.curr_row = (start_row + nrows + self.gap_number)
    if skipby == 'col':
        self.curr_col = (start_col + ncols + self.gap_number)

    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    return 0

insert_image 

insert_image(worksheet, figPath, figScale=(1, 1), loc=None, skipby='row', retCellRange=None)

Insert an image to the sheet.

源代码位于： ExcelMaster/ExcelMaster.py 
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
def insert_image(self, worksheet, figPath, figScale = (1, 1), loc = None, skipby = 'row', retCellRange = None):
    """ Insert an image to the sheet. """
    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col

    start_cell = xl_rowcol_to_cell(start_row, start_col)
    figsize_in_cells = self._get_image_size(figPath = figPath, figScale = figScale, retSizeInCell = True)

    worksheet.insert_image(start_cell, figPath, {"x_scale": figScale[0], "y_scale": figScale[1]})

    # Skipped by Rows/Columns
    if skipby == 'row':
        self.curr_row = (start_row + int(figsize_in_cells[1]) + self.gap_number)
    if skipby == 'col':
        self.curr_col = (start_col + int(figsize_in_cells[0]) + self.gap_number)

    written_range = [start_row, start_col, 
                     start_row + int(figsize_in_cells[1]), 
                     start_col + int(figsize_in_cells[0])]

    # Return written location by Cell Text/Value Range
    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    if self.verbose:
        logging.info(f"Image Written in Cell Range: {self.to_cell_range_text(*written_range)}")

    return 0

write_chart 

write_chart(worksheet, df, y_list, x=None, title='', chart_size=(30, 13), chart_type='line', y_axis_range=(None, None), y_num_format=None, y2_axis=False, loc=None, retChart=False, skipby='row', outputData=False, retCellRange=None, xy_axes_name=('', ''), major_gridlines=False, legend='bottom', line_marker='circle', line_type='solid', chart_style=None, append_to_chart=None)

Write line chart to Excel worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
def write_chart(self, worksheet, df, y_list, x = None, title = "", 
                chart_size = (30, 13), chart_type = "line",
                y_axis_range = (None, None), y_num_format = None,
                y2_axis = False, loc = None, retChart = False, 
                skipby = "row", outputData = False, retCellRange = None,
                xy_axes_name = ("", ""), major_gridlines = False,
                legend = "bottom", line_marker = "circle", line_type = "solid", 
                chart_style = None, append_to_chart = None): 
    """ Write line chart to Excel worksheet."""

    if isinstance(chart_type, str):
        if chart_type == "line":
            chart_type = {'type': 'line'}
        elif chart_type == "column":
            chart_type = {'type': 'column'}
        elif chart_type == "stacked_column":
            chart_type = {'type': 'column', "subtype": "stacked"}
        elif chart_type == "pie":
            chart_type = {"type": "pie"}
        else:
            raise ValueError(" Please select one from 'line', 'column', 'stacked_column' or 'pie'. ")

    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col

    y_axis_range = self.__convert_to_none_tuple(y_axis_range)

    df_t = self._transpose_df_for_chart(df = df, y_list = y_list, x = x)
    if x is None:
        x = list(df.index.names)
    if isinstance(x, str):
        x = [x]
    y = "index" if len(x) == 1 else tuple(["index"] + [''] * (len(x) - 1))
    x_list = [x for x in df_t.columns if x != y]

    data_nrows = df_t.shape[0]
    data_ncols = df_t.shape[1]

    raw_data_ws = self.__add_chart_data_tab("__CHRT_DATA_")

    ## if y not given, then use index value as y series.
    data_index_as_y = True
    if y is None:
        sel_df = df_t[[*x_list]]
    else:
        sel_df = df_t[[y, *x_list]]
        sel_df = sel_df.set_index(y)
        sel_df.index.name = None

    ## if output chart data to current worksheet.
    if outputData:
        raw_data_ws = worksheet
        df_range = self.write_dataframe(worksheet = raw_data_ws, df = sel_df, index = data_index_as_y, title = None, skipby=None, retCellRange="value", loc = (start_row, start_col))
        chart_loc = (df_range[2] + self.gap_number, df_range[1])
    else:
        df_range = self.write_dataframe(worksheet = raw_data_ws, df = sel_df, index = data_index_as_y, title = None, skipby=None, retCellRange="value", loc = (0,0))
        chart_loc = (start_row, start_col)

    x_count = len(x_list)
    nrows = df_t.shape[0]

    data_row_anchor = df_range[0]
    data_col_anchor = df_range[1]
    row_shift = 0

    category_range = [df_range[0], df_range[1] + 1, 
                      df_range[0] + (len(x) - 1), df_range[3]]

    if self.verbose:
        logging.info(f"Category Cell Range: {self.to_cell_range_text(*category_range)}")

    chart = self.workbook.add_chart(chart_type)
    if append_to_chart is not None:
        if self.__validate_input_chart_obj(chart_type = chart_type["type"], input_chart = append_to_chart):
            chart = append_to_chart
        else:
            warnings.warn("WARNING: Can only append data to the chart that has the same chart type as your given one.")

    value_start = len(x) + 1 if len(x) > 1 else len(x)
    for row_shift in range(value_start, value_start + nrows, 1):

        value_range = [data_row_anchor + row_shift, data_col_anchor + 1, 
                       data_row_anchor + row_shift, data_col_anchor + x_count]

        chart.add_series({
            'name':        [raw_data_ws.name, (data_row_anchor + row_shift), data_col_anchor],
            'categories':  [raw_data_ws.name, *category_range],
            'values':      [raw_data_ws.name, *value_range],
            'marker':      {'type': line_marker},
            "line" :       {'dash_type': line_type},
            'data_labels': {'percentage': True} if chart_type['type'] == 'pie' else None,
            'y2_axis':     y2_axis,
        })
        if self.verbose:
            logging.info("Values Cell Range: %s", self.to_cell_range_text(*value_range))

    chart.set_title({'name': title})
    chart.set_legend({'position': str(legend)})
    chart.set_size({"height": chart_size[0] * self.default_row_height, # by row 15
                    "width": chart_size[1] * self.default_col_width}) # by col 8.43

    chart.set_x_axis({"name": xy_axes_name[0]})

    set_y_axis_dict = {"name": xy_axes_name[1], 
                       "major_gridlines": {"visible": int(major_gridlines)},
                       'min': y_axis_range[0], 
                       'max': y_axis_range[1],
                       'num_format': y_num_format}
    if y2_axis:
        chart.set_y2_axis(set_y_axis_dict)
    else:
        chart.set_y_axis(set_y_axis_dict)

    # Setting Chart Style
    if chart_style:
        chart.set_style(chart_style)

    # Need to Return Chart before Insert it to the worksheet.
    if retChart:
        return chart

    worksheet.insert_chart(
        chart_loc[0], 
        chart_loc[1], 
        chart
    )

    written_range = [start_row, start_col, int(chart_loc[0] + chart_size[0]), int(chart_loc[1] + chart_size[1])]
    if outputData:

        written_range = [start_row, start_col, 
                         (start_row + data_nrows + self.gap_number + chart_size[0]),
                         max(df_range[3], start_col + chart_size[1])]

    if skipby == 'row':
        if outputData:
            self.curr_row = (start_row + data_nrows + self.gap_number + chart_size[0] + self.gap_number - 1)
        else:
            self.curr_row = (start_row + chart_size[0] + self.gap_number - 1)
    if skipby == 'col':
        self.curr_col = (start_col + int(chart_size[1]) + self.gap_number)

    if self.verbose:
        logging.info(f"Chart Written in Cell Range: {self.to_cell_range_text(*written_range)}")

    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    return 0

write_combined_chart 

write_combined_chart(worksheet, chart1, chart2, loc=None, chart_size=(30, 13), skipby='row', retCellRange=None)

Combined two chart objects and then write to Excel worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
def write_combined_chart(self, worksheet, chart1, chart2, 
                         loc = None, chart_size = (30, 13), 
                         skipby = "row", retCellRange = None):
    """ Combined two chart objects and then write to Excel worksheet. """

    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col

    chart1.combine(chart2)
    worksheet.insert_chart(xl_rowcol_to_cell(start_row, start_col), chart1)

    written_range = [start_row, start_col, (start_row + chart_size[0]), (start_col + chart_size[1])]

    if skipby == 'row':
        self.curr_row = (start_row + chart_size[0] + self.gap_number - 1)
    if skipby == 'col':
        self.curr_col = (start_col + chart_size[1] + self.gap_number)

    if self.verbose:
        logging.info(f"Chart Written in Cell Range: {self.to_cell_range_text(*written_range)}")

    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    return 0

write_duo_chart 

write_duo_chart(worksheet, df, y1_list, y2_list=None, x=None, c1_type='column', c2_type='line', y1_axis_range=(0, 1), y2_axis_range=None, y1_num_format=None, y2_num_format=None, y1_line_marker='circle', y2_line_marker='circle', y1_line_type='solid', y2_line_type='solid', loc=None, title='', chart_size=(30, 13), xy_axes_name=('', ''), major_gridlines=False, retChart=False, retCellRange=None, skipby='row')

Write duo-chart sharing the same x axis.

源代码位于： ExcelMaster/ExcelMaster.py 
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
def write_duo_chart(self, worksheet, df,
                    y1_list, y2_list = None, x = None,
                    c1_type = "column", c2_type = "line", 
                    y1_axis_range = (0, 1), y2_axis_range = None,
                    y1_num_format = None, y2_num_format = None,
                    y1_line_marker = "circle", y2_line_marker = "circle",
                    y1_line_type = "solid", y2_line_type = "solid",
                    loc = None, title = "", chart_size = (30, 13),
                    xy_axes_name = ("", ""), major_gridlines = False,
                    retChart = False, retCellRange = None,
                    skipby = "row"):
    """ Write duo-chart sharing the same x axis. """

    start_row = loc[0] if loc else self.curr_row
    start_col = loc[1] if loc else self.curr_col

    y2_axis = True
    if y2_list is None:
        y2_axis = False

    if y2_axis_range is None:
        y2_axis_range = y1_axis_range

    xy_name = (xy_axes_name[0], xy_axes_name[1])
    xy2_name = (xy_axes_name[0], xy_axes_name[1])
    if y2_axis and len(xy_axes_name) >= 3:
        xy_name = (xy_axes_name[0], xy_axes_name[1])
        xy2_name = (xy_axes_name[0], xy_axes_name[2])
    if y2_axis and len(xy_axes_name) < 3:
        xy_name = (xy_axes_name[0], xy_axes_name[1])
        xy2_name = (xy_axes_name[0], "")

    chart1 = self.write_chart(df = df, 
                              x = x, 
                              y_list = y1_list, 
                              worksheet = worksheet, 
                              title = title,
                              chart_type = c1_type, 
                              chart_size = chart_size,
                              y_axis_range = y1_axis_range,
                              xy_axes_name = xy_name,
                              major_gridlines = major_gridlines,
                              y_num_format = y1_num_format,
                              line_type = y1_line_type,
                              line_marker = y1_line_marker,
                              retChart = True)

    chart2 = self.write_chart(df = df, 
                              x = x,
                              y_list = y2_list, 
                              worksheet=worksheet, 
                              title = title, 
                              chart_type = c2_type, 
                              chart_size = chart_size,
                              y_axis_range = y2_axis_range,
                              y2_axis = y2_axis,
                              xy_axes_name = xy2_name,
                              major_gridlines = False,
                              y_num_format = y2_num_format,
                              line_type = y2_line_type,
                              line_marker = y2_line_marker,
                              retChart=True)

    # Need to Return Chart before Insert it to the worksheet.
    if retChart:
        return (chart1, chart2)

    cell_range = self.write_combined_chart(worksheet, 
                              chart1, chart2, 
                              loc = loc, chart_size = chart_size, 
                              skipby = skipby, retCellRange = retCellRange)

    return cell_range

write_text_by_dict 

write_text_by_dict(worksheet, dict_cells)

Write text using Python dictionary.

源代码位于： ExcelMaster/ExcelMaster.py 
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
def write_text_by_dict(self, worksheet, dict_cells):
    """ Write text using Python dictionary. """
    for cell in dict_cells:
        list_contents = dict_cells[cell]

        if ':' in cell:
            text, cell_format = list_contents
            worksheet.merge_range(cell, text, self.dict_cell_format[cell_format])

        else:
            if len(list_contents) == 1:
                list_items = []

                # Text formats begin with '~~~'
                list_mixed_items = list_contents[0]
                for item in list_mixed_items:
                    if item.startswith('~~~'):
                        cell_format = item.split('~~~')[1]
                        item = self.dict_cell_format[cell_format]

                        list_items.append(item)
                    else:
                        list_items.append(item)

                worksheet.write_rich_string(cell, *list_items)

            else:
                text, cell_format = list_contents
                worksheet.write(cell, text, self.dict_cell_format[cell_format])

write_text_content 

write_text_content(worksheet, input_text=None, txt_path=None, loc=None, retCellRange=None)

Write text content line by line to the worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
def write_text_content(self, worksheet, input_text = None, txt_path = None, loc = None, retCellRange = None):
    """ Write text content line by line to the worksheet. """

    row_anchor = loc[0] if loc else self.curr_row
    col_anchor = loc[1] if loc else self.curr_col

    start_row = row_anchor
    start_col = col_anchor

    if (input_text) and (txt_path):
        raise ValueError("Please give either input_text or txt_path, not both !!!")

    if (input_text is None) and (txt_path is None):
        raise ValueError("Please specify either input_text or txt_path.")

    if txt_path is not None:
        file_notes = open(txt_path, 'r')
        textlines = file_notes.readlines()

    if input_text is not None:
        textlines = input_text.split("\n")

    for line in textlines:
        # Write text line by line
        loc = xl_rowcol_to_cell(row_anchor, col_anchor)

        if " [>] " in line:
            line_split = line.split(" [>] ")
            col_shift = 0
            for sub_line in line_split:
                sub_line = sub_line.rstrip()
                self.__parse_line_by_format_sign(worksheet = worksheet, loc = loc, line = sub_line)
                col_shift += 1
                loc = xl_rowcol_to_cell(row_anchor, col_anchor + col_shift)
        else:
            self.__parse_line_by_format_sign(worksheet = worksheet, loc = loc, line = line)

        row_anchor += 1

    self.curr_row = (row_anchor - 1)

    end_row = row_anchor
    end_col = col_anchor

    written_range = [start_row, start_col, end_row, end_col]

    if self.verbose:
        logging.info(f"Text Written in Cell Range: {self.to_cell_range_text(*written_range)}")

    if retCellRange == "text":
        return self.to_cell_range_text(*written_range)
    if retCellRange == "value":
        return written_range

    return 0

plot_boxplot staticmethod 

plot_boxplot(df, x, y, y_percentage=False, colored_box=True, color_grp=(10, 1), title='', fontsize=14, figsize=(8, 6), show_fig=True, img_path=None, transp_bg=False)

Plot Box Plot Chart using matplotlib.

源代码位于： ExcelMaster/ExcelMaster.py 
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
@staticmethod
def plot_boxplot(df, x, y, y_percentage = False, colored_box = True, color_grp = (10, 1), title = "", fontsize = 14, figsize = (8, 6), show_fig = True, img_path = None, transp_bg = False):
    """ Plot Box Plot Chart using matplotlib. """

    plt.style.use('default')

    fig, ax = plt.subplots(1, 1, figsize = figsize, dpi=200)

    box_plot_data = convert_to_boxplot_data(df, x, y, True)

    bplot = ax.boxplot(box_plot_data.values(), patch_artist=colored_box, widths = 0.4)
    ax.set_xticklabels(box_plot_data.keys(), fontsize = fontsize)
    ax.set_ylabel(string_proc(y), color='black', fontsize = fontsize)
    ax.set_xlabel(string_proc(x), color='black', fontsize = fontsize)
    ax.tick_params(axis='both', labelsize=fontsize)
    ax.grid(True, 'major', 'y', ls='--', lw=.5, c='k', alpha=.3)
    ax.set_title(title, fontsize=fontsize + 4)

    if colored_box:
        colors = color_input_validation(color_grp, len(box_plot_data.keys()))
        for patch, color in zip(bplot['boxes'], colors):
            patch.set_facecolor(color)
            patch.set_alpha(.7)

    if y_percentage:
        plt.gca().yaxis.set_major_formatter(PercentFormatter(100)) 
    plt.tight_layout()

    if show_fig:
        plt.show()

    if img_path:
        fig.savefig(img_path, transparent = transp_bg, dpi=200)

    plt.close()
    return fig, ax

write_boxplot 

write_boxplot(ws, df, x, y, y_percentage=False, colored_box=True, color_grp=(10, 1), title='', fontsize=14, figsize=(30, 13), show_fig=False, img_path=None, transp_bg=False, loc=None, skipby='row', retCellRange=None)

Write boxplot to Worksheet.

源代码位于： ExcelMaster/ExcelMaster.py 
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
def write_boxplot(self, ws, df, x, y, y_percentage = False, colored_box = True, color_grp = (10, 1), title = "", 
                  fontsize = 14, figsize = (30, 13), show_fig = False, img_path = None, transp_bg = False,
                  loc = None, skipby = "row", retCellRange = None):
    """ Write boxplot to Worksheet. """

    currTime = getCurrentDateTime()
    rn = str(random.randrange(0, 1000))
    rn_num = currTime + rn
    tmp_image_path = f"./.tmp_image_{rn_num}.png"

    ExcelMaster.plot_boxplot(df = df, 
                             x = x, y = y, 
                             y_percentage = y_percentage, 
                             colored_box = colored_box, 
                             color_grp = color_grp, 
                             title = title, 
                             fontsize = fontsize, 
                             show_fig = show_fig, 
                             transp_bg = transp_bg,
                             img_path = tmp_image_path)

    self._resize_image(tmp_image_path, figsize, tmp_image_path)
    ret_range = self.insert_image(ws, figPath=tmp_image_path, figScale=(1, 1), loc = loc, skipby = skipby, retCellRange = retCellRange)

    return ret_range

getStartDateofLatestWeek 

getStartDateofLatestWeek(retStr=True)

Date of first day of last week.

源代码位于： ExcelMaster/Utility.py 
15
16
17
18
19
20
21
22
23
24
25
def getStartDateofLatestWeek(retStr=True):
    """ Date of first day of last week. """
    import datetime
    today = datetime.date.today()
    curr_wk = today.strftime("%W")
    d = f"{str(today.year)}-W{curr_wk}"
    r = datetime.datetime.strptime(d + '-1', "%Y-W%W-%w")
    res = (r + datetime.timedelta(days=-1))
    if retStr:
        return res.strftime("%Y-%m-%d")
    return res

getLastCompletedVintage 

getLastCompletedVintage(start_date=None, format='%Y-%m-%d', vintage=False)

Last Completed Vintage

源代码位于： ExcelMaster/Utility.py 
27
28
29
30
31
32
33
34
35
36
37
38
39
def getLastCompletedVintage(start_date = None, format="%Y-%m-%d", vintage=False):
    """ Last Completed Vintage """
    import datetime

    todayDate = datetime.date.today()

    if start_date is not None:
        todayDate = datetime.datetime.strptime(start_date, format).date()    

    lastM = todayDate.replace(day=1) - datetime.timedelta(days=1)
    if vintage:
        return int(lastM.strftime(format)[0:7].replace("-",""))
    return lastM.strftime(format)

vin2quar 

vin2quar(strDate)

String Vintage to Quarter (if compeleted month).

源代码位于： ExcelMaster/Utility.py 
41
42
43
44
45
46
47
48
49
def vin2quar(strDate):
    """ String Vintage to Quarter (if compeleted month). """
    year = int(strDate[:4])
    month = int(strDate[4:6])
    completed_q = [3, 6, 9, 12]
    if month in completed_q:
        q = (month-1)//3 + 1
        return str(year) + "Q" + str(q)
    return strDate

list_files 

list_files(location, pattern)

List all files.

源代码位于： ExcelMaster/Utility.py 
51
52
53
54
55
56
57
58
59
def list_files(location, pattern):
    """ List all files. """
    import re
    res = []
    for root, dirs, files in os.walk(location):
        for file in files:
            if re.search(pattern, file):
                 res.append(file)
    return res

getCurrentDateTime 

getCurrentDateTime(fmt='%Y%m%d%H%M%S')

Get Current DateTime

源代码位于： ExcelMaster/Utility.py 
61
62
63
64
def getCurrentDateTime(fmt = "%Y%m%d%H%M%S"):
    """ Get Current DateTime"""
    import datetime
    return datetime.datetime.now().strftime(fmt)

input_table_proc 

input_table_proc(tbl)

Process Input Table.

源代码位于： ExcelMaster/Utility.py 
66
67
68
69
def input_table_proc(tbl):
    """ Process Input Table. """
    tbl.columns = [x.lower() for x in tbl.columns]
    return tbl

get_file_extension 

get_file_extension(input_path)

Get File Extentsion for a given file Path.

源代码位于： ExcelMaster/Utility.py 
71
72
73
def get_file_extension(input_path):
    """ Get File Extentsion for a given file Path. """
    return os.path.splitext(input_path)[1]

input_validation 

input_validation(x, sep=',')

Input Validation.

源代码位于： ExcelMaster/Utility.py 
75
76
77
78
79
80
81
82
83
84
85
86
87
88
def input_validation(x, sep=","):
    """ Input Validation. """
    import os
    if isinstance(x, str):
        if get_file_extension(x) == ".sas7bdat":
            res = pd.read_sas(x, encoding="latin-1")
        else:
            res = pd.read_csv(x, sep = sep)
        res = input_table_proc(res)
        return res
    elif isinstance(x, pd.DataFrame):
        return input_table_proc(x)
    else:
        raise AttributeError("Only Support csv/sas7bdat Path or Panda DataFrame as Input!!!")

val_input_condition 

val_input_condition(target, condition=('>', 20))

Condition Tuple Validation.

源代码位于： ExcelMaster/Utility.py 
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
def val_input_condition(target, condition = (">", 20)):
    """ Condition Tuple Validation. """
    if isinstance(condition, str):
        return (target == condition)

    else:
        operator = condition[0].strip().lower()
        value = float(condition[1])

        if operator == '>' or operator == 'gt':
            return (target > value)
        elif operator == '<' or operator == 'lt':
            return (target < value)
        elif operator == '=' or operator == 'eq':
            return (target == value)
        elif operator == '>=' or operator == 'gte':
            return (target >= value)
        elif operator == '<=' or operator == 'lte':
            return (target <= value)
        elif operator == '=' or operator == 'eq':
            return (target == value)

tanspose_dataframe 

tanspose_dataframe(df, index_col)

Transpose Pandas DataFrame.

源代码位于： ExcelMaster/Utility.py 
115
116
117
118
def tanspose_dataframe(df, index_col):
    """ Transpose Pandas DataFrame. """
    df = df.set_index(index_col).T.reset_index()
    return df

convert_perc_str_to_float 

convert_perc_str_to_float(df, cols)

Percentage to Float.

源代码位于： ExcelMaster/Utility.py 
120
121
122
123
124
125
def convert_perc_str_to_float(df, cols):
    """ Percentage to Float. """
    for col in cols:
        if str(df[col].dtypes) == 'object':
            df[col] = df[col].str.rstrip('%').astype('float') / 100
    return df

color_hex2rgb 

color_hex2rgb(hex_code)

Convert Color Hex Code to RGB Tuple.

源代码位于： ExcelMaster/Utility.py 
127
128
129
130
131
def color_hex2rgb(hex_code):
    """ Convert Color Hex Code to RGB Tuple. """
    hex_code = hex_code.lower()
    h = hex_code.lstrip('#')
    return tuple(int(h[i:i+2], 16) for i in (0, 2, 4))

get_color_set 

get_color_set(n, start_num=0, step=1, retName=False, lookupName=None)

Return a set of color code without replacement.

源代码位于： ExcelMaster/Utility.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
def get_color_set(n, start_num = 0, step = 1, retName = False, lookupName = None):
    """ Return a set of color code without replacement. """
    import matplotlib.colors as mcolors
    import re

    colors = list(mcolors.XKCD_COLORS.items())
    color_set = {}

    for i in range(start_num, start_num + n * step, step):
        name = colors[i][0].replace("xkcd:", "")
        color = colors[i][1]
        color_set[name] = color

    if lookupName:
        color_set = {}
        i = 0
        for name, color in colors:
            if len(color_set.items()) == n:
                break
            if re.search(lookupName, name):
                color_set[name.replace("xkcd:", "")] = color
            i += 1

    if retName:
        return color_set
    return list(color_set.values())

string_proc 

string_proc(x)

Process a given String.

源代码位于： ExcelMaster/Utility.py 
160
161
162
163
164
165
def string_proc(x):
    """ Process a given String. """
    x_list = x.split("_")
    x_list = [x.strip().capitalize() for x in x_list]
    x = " ".join(x_list)
    return x

convert_to_boxplot_data 

convert_to_boxplot_data(df, x, y, y_percentage=False)

Convert dataframe to boxplot data.

源代码位于： ExcelMaster/Utility.py 
167
168
169
170
171
172
173
174
def convert_to_boxplot_data(df, x, y, y_percentage = False):
    """ Convert dataframe to boxplot data. """
    x_unique_value = df[x].sort_values().unique().tolist()

    box_plot_data = {}
    for v in x_unique_value:
        box_plot_data[v] = [num * 100 if y_percentage else num for num in df[df[x] == v][y].tolist()]
    return box_plot_data

color_input_validation 

color_input_validation(color_grp, val_n)

Perform Color Input Validation.

源代码位于： ExcelMaster/Utility.py 
176
177
178
179
180
181
182
183
184
185
186
187
188
def color_input_validation(color_grp, val_n):
    """ Perform Color Input Validation. """
    if isinstance(color_grp, tuple) and len(color_grp) == 2:
        # Customize colors
        cols = get_color_set(val_n, color_grp[0], color_grp[1], False)
        colors = cols
    elif isinstance(color_grp, str):
        colors = [color_grp] * val_n
    elif (isinstance(color_grp, list)) and (all([isinstance(x, str) for x in color_grp])) and (len(color_grp) == val_n):
        colors = color_grp
    else:
        raise ValueError("Please give valid color_grp: tuple of two numbers, list of color code or a single color code.")
    return colors

get_metric_shift 

get_metric_shift(data, metric_name, nvars_col='nvars')

Calculate Metric Shift for Variable Reduction.

源代码位于： ExcelMaster/Utility.py 
190
191
192
193
194
def get_metric_shift(data, metric_name, nvars_col = "nvars"):
    """ Calculate Metric Shift for Variable Reduction. """
    metric_lift = (data[metric_name] - data[metric_name].shift(1))
    nvars_reduced = (data[nvars_col] - data[nvars_col].shift(1))
    return (metric_lift / nvars_reduced).fillna(0)

get_metrics_shift 

get_metrics_shift(data, metric_cols)

Get Shift for List of Metrics.

源代码位于： ExcelMaster/Utility.py 
196
197
198
199
200
201
def get_metrics_shift(data, metric_cols):
    """ Get Shift for List of Metrics."""
    for metric in metric_cols:
        if metric.startswith(tuple(metric_cols)):
            data[metric+"_shift"] = get_metric_shift(data, metric)
    return data

compute_overfitting_shift 

compute_overfitting_shift(data, sample_prefix)

Calculate Overfitting Performance Shift.

源代码位于： ExcelMaster/Utility.py 
203
204
205
206
207
208
209
210
211
212
213
def compute_overfitting_shift(data, sample_prefix):
    """ Calculate Overfitting Performance Shift. """
    b_metrics = [x for x in data.columns if x.startswith(sample_prefix[0])]
    o_metrics = [x for x in data.columns if x.startswith(sample_prefix[1])]

    if len(b_metrics) == len(o_metrics):
        for b_metric, o_metric in zip(b_metrics, o_metrics):
            data[o_metric+"_shift"] = data[o_metric].div(data[b_metric]) - 1
        return data

    raise ValueError("The lengths of metrics between two samples are the the same in the given dataset!")

proc_psi_raw_report 

proc_psi_raw_report(psi_raw_table, psi_title, keep_list=None, varname='variable', upper=True)

Processing Raw PSI Report generated from Takecopter.

源代码位于： ExcelMaster/Utility.py 
215
216
217
218
219
220
221
222
223
224
225
def proc_psi_raw_report(psi_raw_table, psi_title, keep_list = None, varname = "variable", upper=True):
    """ Processing Raw PSI Report generated from Takecopter. """
    psi_table = input_validation(psi_raw_table)
    psi_table = psi_table.rename(columns={"var_for_psi":varname})
    psi_table = psi_table.set_index(varname)
    if upper:
        psi_table.columns = [x.upper() for x in psi_table.columns]
    psi_table.columns = [[psi_title]*len(psi_table.columns),psi_table.columns]
    if keep_list:
        psi_table = psi_table[[(psi_title, x) for x in keep_list]]
    return psi_table

get_mean_risk 

get_mean_risk(bivar_single_attr, value_range_col=['min_indep', 'max_indep'], dep_col='dep')

get average risk

源代码位于： ExcelMaster/Utility.py 
227
228
229
230
231
232
233
def get_mean_risk(bivar_single_attr, value_range_col = ['min_indep', 'max_indep'], dep_col = "dep"):
    """get average risk"""
    mean_wo_nan = bivar_single_attr.dropna(how = "all", subset=value_range_col)[dep_col].mean()
    mean_w_na = bivar_single_attr[dep_col].mean()
    bivar_single_attr["mean"] = mean_w_na
    bivar_single_attr["mean_no_nan"] = mean_wo_nan
    return bivar_single_attr

报告模板 — Template

Template

getStartDateofLatestWeek 

getStartDateofLatestWeek(retStr=True)

Date of first day of last week.

源代码位于： ExcelMaster/Utility.py 
15
16
17
18
19
20
21
22
23
24
25
def getStartDateofLatestWeek(retStr=True):
    """ Date of first day of last week. """
    import datetime
    today = datetime.date.today()
    curr_wk = today.strftime("%W")
    d = f"{str(today.year)}-W{curr_wk}"
    r = datetime.datetime.strptime(d + '-1', "%Y-W%W-%w")
    res = (r + datetime.timedelta(days=-1))
    if retStr:
        return res.strftime("%Y-%m-%d")
    return res

getLastCompletedVintage 

getLastCompletedVintage(start_date=None, format='%Y-%m-%d', vintage=False)

Last Completed Vintage

源代码位于： ExcelMaster/Utility.py 
27
28
29
30
31
32
33
34
35
36
37
38
39
def getLastCompletedVintage(start_date = None, format="%Y-%m-%d", vintage=False):
    """ Last Completed Vintage """
    import datetime

    todayDate = datetime.date.today()

    if start_date is not None:
        todayDate = datetime.datetime.strptime(start_date, format).date()    

    lastM = todayDate.replace(day=1) - datetime.timedelta(days=1)
    if vintage:
        return int(lastM.strftime(format)[0:7].replace("-",""))
    return lastM.strftime(format)

vin2quar 

vin2quar(strDate)

String Vintage to Quarter (if compeleted month).

源代码位于： ExcelMaster/Utility.py 
41
42
43
44
45
46
47
48
49
def vin2quar(strDate):
    """ String Vintage to Quarter (if compeleted month). """
    year = int(strDate[:4])
    month = int(strDate[4:6])
    completed_q = [3, 6, 9, 12]
    if month in completed_q:
        q = (month-1)//3 + 1
        return str(year) + "Q" + str(q)
    return strDate

list_files 

list_files(location, pattern)

List all files.

源代码位于： ExcelMaster/Utility.py 
51
52
53
54
55
56
57
58
59
def list_files(location, pattern):
    """ List all files. """
    import re
    res = []
    for root, dirs, files in os.walk(location):
        for file in files:
            if re.search(pattern, file):
                 res.append(file)
    return res

getCurrentDateTime 

getCurrentDateTime(fmt='%Y%m%d%H%M%S')

Get Current DateTime

源代码位于： ExcelMaster/Utility.py 
61
62
63
64
def getCurrentDateTime(fmt = "%Y%m%d%H%M%S"):
    """ Get Current DateTime"""
    import datetime
    return datetime.datetime.now().strftime(fmt)

input_table_proc 

input_table_proc(tbl)

Process Input Table.

源代码位于： ExcelMaster/Utility.py 
66
67
68
69
def input_table_proc(tbl):
    """ Process Input Table. """
    tbl.columns = [x.lower() for x in tbl.columns]
    return tbl

get_file_extension 

get_file_extension(input_path)

Get File Extentsion for a given file Path.

源代码位于： ExcelMaster/Utility.py 
71
72
73
def get_file_extension(input_path):
    """ Get File Extentsion for a given file Path. """
    return os.path.splitext(input_path)[1]

input_validation 

input_validation(x, sep=',')

Input Validation.

源代码位于： ExcelMaster/Utility.py 
75
76
77
78
79
80
81
82
83
84
85
86
87
88
def input_validation(x, sep=","):
    """ Input Validation. """
    import os
    if isinstance(x, str):
        if get_file_extension(x) == ".sas7bdat":
            res = pd.read_sas(x, encoding="latin-1")
        else:
            res = pd.read_csv(x, sep = sep)
        res = input_table_proc(res)
        return res
    elif isinstance(x, pd.DataFrame):
        return input_table_proc(x)
    else:
        raise AttributeError("Only Support csv/sas7bdat Path or Panda DataFrame as Input!!!")

val_input_condition 

val_input_condition(target, condition=('>', 20))

Condition Tuple Validation.

源代码位于： ExcelMaster/Utility.py 
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
def val_input_condition(target, condition = (">", 20)):
    """ Condition Tuple Validation. """
    if isinstance(condition, str):
        return (target == condition)

    else:
        operator = condition[0].strip().lower()
        value = float(condition[1])

        if operator == '>' or operator == 'gt':
            return (target > value)
        elif operator == '<' or operator == 'lt':
            return (target < value)
        elif operator == '=' or operator == 'eq':
            return (target == value)
        elif operator == '>=' or operator == 'gte':
            return (target >= value)
        elif operator == '<=' or operator == 'lte':
            return (target <= value)
        elif operator == '=' or operator == 'eq':
            return (target == value)

tanspose_dataframe 

tanspose_dataframe(df, index_col)

Transpose Pandas DataFrame.

源代码位于： ExcelMaster/Utility.py 
115
116
117
118
def tanspose_dataframe(df, index_col):
    """ Transpose Pandas DataFrame. """
    df = df.set_index(index_col).T.reset_index()
    return df

convert_perc_str_to_float 

convert_perc_str_to_float(df, cols)

Percentage to Float.

源代码位于： ExcelMaster/Utility.py 
120
121
122
123
124
125
def convert_perc_str_to_float(df, cols):
    """ Percentage to Float. """
    for col in cols:
        if str(df[col].dtypes) == 'object':
            df[col] = df[col].str.rstrip('%').astype('float') / 100
    return df

color_hex2rgb 

color_hex2rgb(hex_code)

Convert Color Hex Code to RGB Tuple.

源代码位于： ExcelMaster/Utility.py 
127
128
129
130
131
def color_hex2rgb(hex_code):
    """ Convert Color Hex Code to RGB Tuple. """
    hex_code = hex_code.lower()
    h = hex_code.lstrip('#')
    return tuple(int(h[i:i+2], 16) for i in (0, 2, 4))

get_color_set 

get_color_set(n, start_num=0, step=1, retName=False, lookupName=None)

Return a set of color code without replacement.

源代码位于： ExcelMaster/Utility.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
def get_color_set(n, start_num = 0, step = 1, retName = False, lookupName = None):
    """ Return a set of color code without replacement. """
    import matplotlib.colors as mcolors
    import re

    colors = list(mcolors.XKCD_COLORS.items())
    color_set = {}

    for i in range(start_num, start_num + n * step, step):
        name = colors[i][0].replace("xkcd:", "")
        color = colors[i][1]
        color_set[name] = color

    if lookupName:
        color_set = {}
        i = 0
        for name, color in colors:
            if len(color_set.items()) == n:
                break
            if re.search(lookupName, name):
                color_set[name.replace("xkcd:", "")] = color
            i += 1

    if retName:
        return color_set
    return list(color_set.values())

string_proc 

string_proc(x)

Process a given String.

源代码位于： ExcelMaster/Utility.py 
160
161
162
163
164
165
def string_proc(x):
    """ Process a given String. """
    x_list = x.split("_")
    x_list = [x.strip().capitalize() for x in x_list]
    x = " ".join(x_list)
    return x

convert_to_boxplot_data 

convert_to_boxplot_data(df, x, y, y_percentage=False)

Convert dataframe to boxplot data.

源代码位于： ExcelMaster/Utility.py 
167
168
169
170
171
172
173
174
def convert_to_boxplot_data(df, x, y, y_percentage = False):
    """ Convert dataframe to boxplot data. """
    x_unique_value = df[x].sort_values().unique().tolist()

    box_plot_data = {}
    for v in x_unique_value:
        box_plot_data[v] = [num * 100 if y_percentage else num for num in df[df[x] == v][y].tolist()]
    return box_plot_data

color_input_validation 

color_input_validation(color_grp, val_n)

Perform Color Input Validation.

源代码位于： ExcelMaster/Utility.py 
176
177
178
179
180
181
182
183
184
185
186
187
188
def color_input_validation(color_grp, val_n):
    """ Perform Color Input Validation. """
    if isinstance(color_grp, tuple) and len(color_grp) == 2:
        # Customize colors
        cols = get_color_set(val_n, color_grp[0], color_grp[1], False)
        colors = cols
    elif isinstance(color_grp, str):
        colors = [color_grp] * val_n
    elif (isinstance(color_grp, list)) and (all([isinstance(x, str) for x in color_grp])) and (len(color_grp) == val_n):
        colors = color_grp
    else:
        raise ValueError("Please give valid color_grp: tuple of two numbers, list of color code or a single color code.")
    return colors

get_metric_shift 

get_metric_shift(data, metric_name, nvars_col='nvars')

Calculate Metric Shift for Variable Reduction.

源代码位于： ExcelMaster/Utility.py 
190
191
192
193
194
def get_metric_shift(data, metric_name, nvars_col = "nvars"):
    """ Calculate Metric Shift for Variable Reduction. """
    metric_lift = (data[metric_name] - data[metric_name].shift(1))
    nvars_reduced = (data[nvars_col] - data[nvars_col].shift(1))
    return (metric_lift / nvars_reduced).fillna(0)

get_metrics_shift 

get_metrics_shift(data, metric_cols)

Get Shift for List of Metrics.

源代码位于： ExcelMaster/Utility.py 
196
197
198
199
200
201
def get_metrics_shift(data, metric_cols):
    """ Get Shift for List of Metrics."""
    for metric in metric_cols:
        if metric.startswith(tuple(metric_cols)):
            data[metric+"_shift"] = get_metric_shift(data, metric)
    return data

compute_overfitting_shift 

compute_overfitting_shift(data, sample_prefix)

Calculate Overfitting Performance Shift.

源代码位于： ExcelMaster/Utility.py 
203
204
205
206
207
208
209
210
211
212
213
def compute_overfitting_shift(data, sample_prefix):
    """ Calculate Overfitting Performance Shift. """
    b_metrics = [x for x in data.columns if x.startswith(sample_prefix[0])]
    o_metrics = [x for x in data.columns if x.startswith(sample_prefix[1])]

    if len(b_metrics) == len(o_metrics):
        for b_metric, o_metric in zip(b_metrics, o_metrics):
            data[o_metric+"_shift"] = data[o_metric].div(data[b_metric]) - 1
        return data

    raise ValueError("The lengths of metrics between two samples are the the same in the given dataset!")

proc_psi_raw_report 

proc_psi_raw_report(psi_raw_table, psi_title, keep_list=None, varname='variable', upper=True)

Processing Raw PSI Report generated from Takecopter.

源代码位于： ExcelMaster/Utility.py 
215
216
217
218
219
220
221
222
223
224
225
def proc_psi_raw_report(psi_raw_table, psi_title, keep_list = None, varname = "variable", upper=True):
    """ Processing Raw PSI Report generated from Takecopter. """
    psi_table = input_validation(psi_raw_table)
    psi_table = psi_table.rename(columns={"var_for_psi":varname})
    psi_table = psi_table.set_index(varname)
    if upper:
        psi_table.columns = [x.upper() for x in psi_table.columns]
    psi_table.columns = [[psi_title]*len(psi_table.columns),psi_table.columns]
    if keep_list:
        psi_table = psi_table[[(psi_title, x) for x in keep_list]]
    return psi_table

get_mean_risk 

get_mean_risk(bivar_single_attr, value_range_col=['min_indep', 'max_indep'], dep_col='dep')

get average risk

源代码位于： ExcelMaster/Utility.py 
227
228
229
230
231
232
233
def get_mean_risk(bivar_single_attr, value_range_col = ['min_indep', 'max_indep'], dep_col = "dep"):
    """get average risk"""
    mean_wo_nan = bivar_single_attr.dropna(how = "all", subset=value_range_col)[dep_col].mean()
    mean_w_na = bivar_single_attr[dep_col].mean()
    bivar_single_attr["mean"] = mean_w_na
    bivar_single_attr["mean_no_nan"] = mean_wo_nan
    return bivar_single_attr

get_pva_report 

get_pva_report(em, ws, gains_result, sample_list, nbins=10, varcol='variable', chart_scale=(10, 10))

Plot PVA Table by Segment across Sample.

源代码位于： ExcelMaster/Template.py 
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
def get_pva_report(em, ws, gains_result, sample_list, nbins = 10, varcol = "variable", chart_scale = (10, 10)):
    """ Plot PVA Table by Segment across Sample. """
    gains_results = input_validation(gains_result)

    varcol = varcol.lower()
    segs = gains_results["seg_name"].unique().tolist()
    chart_size = (nbins + chart_scale[0], (nbins + chart_scale[1])/2)

    # em.reset_curr_loc()
    em.merge_col(worksheet=ws, ncols=5, text="PVA Charts")

    em.gap_number = 2
    for seg in segs:
        """ Plot PVA charts by segment row by row """
        ########## Data Wrangling ###############
        example = gains_results.query(f"seg_name == '{seg}'").dropna()
        example = convert_perc_str_to_float(example, ["interval_bad_rate"])

        cols = ["rank", "sample", "mean_score", "interval_bad_rate"]

        example_fnl = example[cols].astype({"rank":int}).melt(id_vars = ["rank", "sample"], value_vars = ["mean_score", "interval_bad_rate"])
        example_fnl["score_type"] = example_fnl[varcol].str.replace("mean_score", "predicted").replace("interval_bad_rate", "actual")
        example_fnl = example_fnl.pivot(index = ["rank"], columns=["sample", "score_type"], values = "value")
        col_order = example_fnl.columns.get_level_values(0).unique().tolist()
        fnl_out_res = example_fnl[col_order]

        ########### Insert Data and Charts to the Worksheet ###################
        em.write_text_content(worksheet=ws, input_text=f"{seg} [[ORANGE_H3]] \n")

        # sample_list = example["sample"].unique().tolist()
        chart_loc = {}
        for sample in sample_list:
            """ Plot PVA charts by sample column by column"""
            example_sample = example.query(f"sample == '{sample}'").dropna()
            loc = em.write_chart(ws, df = example_sample, x="rank", 
                                  y_list=["mean_score", "interval_bad_rate"], 
                                  title=f"PVA Chart ({sample.upper()}) {seg}", 
                                  chart_size=chart_size, 
                                  chart_type="line", 
                                  major_gridlines=False, 
                                  xy_axes_name=("Quantiles", "% of Bads"), 
                                  y_axis_range=(0, 1), 
                                  y_num_format="0.00%",
                                  skipby="col", retCellRange="value")
            chart_loc[sample] = loc

        loc4 = em.write_dataframe(worksheet=ws, df=fnl_out_res, title=f"PVA Chart ({seg})", index=True, skipby="row", retCellRange="value")

        tbl_value_range = [x + 2 if i == 0 else x + 1 
                                 if i == 1 else x + 2
                                 if i == 2 else x
                           for i, x in enumerate(loc4)]

        em.set_cell_format(ws, tbl_value_range, "----")
        em.set_cell_format(ws, tbl_value_range, "NUM%.3")

        chart1_loc = chart_loc[sample_list[0]]
        em.curr_row = chart1_loc[2] + em.gap_number
        em.curr_col = chart1_loc[1]
    return ws

get_bivar_report 

get_bivar_report(em, ws, attr_info, bivar, sample_list, varcol='varname', sample_col='sample', x_cols=['min_indep', 'max_indep'], n_col='_freq_', dep_col='dep', chart_size=(20, 10), average_risk_line=False)

Get Bivar Report by Attribute across Samples.

源代码位于： ExcelMaster/Template.py 
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
def get_bivar_report(em, ws, attr_info, bivar, sample_list, varcol = "varname", sample_col = "sample", x_cols = ["min_indep", "max_indep"], n_col = "_freq_", dep_col = "dep", chart_size = (20, 10), average_risk_line = False):
    """ Get Bivar Report by Attribute across Samples. """

    ##### Worksheet 1 ######
    em.merge_col(worksheet = ws, ncols=5, text = "Bivar Plot")

    bivar_table = input_validation(bivar)
    attr_info_table = input_validation(attr_info)

    varcol = varcol.lower()
    sample_col = sample_col.lower()
    x_cols = [x.lower() for x in x_cols]
    n_col = n_col.lower()
    dep_col = dep_col.lower()

    bivar_table.columns = [x.lower() for x in bivar_table.columns]
    attr_info_table.columns = [x.lower() for x in attr_info_table.columns]

    var_by_varimp = attr_info_table[varcol].str.lower().tolist()
    bivar_table["indep_range"] = "[" + bivar_table[x_cols[0]].astype(str) + ", " \
                                     + bivar_table[x_cols[1]].astype(str) + "]"

    for var in var_by_varimp:
        """ Plot Bivar Chart by Variable Row by Row. """

        em.gap_number = 1
        singe_attr_info = attr_info_table.query(f"{varcol} == '{var.upper()}'")
        em.write_dataframe(ws, df = singe_attr_info, index = False, 
                           title =f"Information for Attribute {var.upper()}", skipby="row", retCellRange="value")
        var_desc = singe_attr_info["description"].values[0]

        em.gap_number = 2
        chart_loc = {}
        for sample in sample_list:
            """ Plot Bivar Chart Column by Column """
            single_attr_bivar_sample = bivar_table.query(f"{varcol} == '{var}' and {sample_col} == '{sample}'")
            single_attr_bivar_sample = get_mean_risk(single_attr_bivar_sample)

            loc = em.write_duo_chart(worksheet = ws, 
                                       df = single_attr_bivar_sample, 
                                       y1_list = [n_col], 
                                       y2_list = [dep_col], 
                                       x = "indep_range",
                                       c1_type = "column", 
                                       c2_type = "line", 
                                       y1_axis_range = None,
                                       y2_axis_range = None, 
                                       title = f"Bivar Plot ({sample.upper()}) for Attribute {var.upper()}", 
                                       chart_size = chart_size,
                                       xy_axes_name = (var_desc, "N", "Bad Rate"),
                                       major_gridlines=False,
                                       retChart = average_risk_line, 
                                       y2_num_format = "0.00%",
                                       skipby = "col", 
                                       retCellRange="value")

            if average_risk_line:

                column_chart = loc[0]
                line_chart = loc[1]
                fnl_line_chart = em.write_chart(worksheet = ws, 
                                           df = single_attr_bivar_sample, 
                                           y_list = ['mean', 'mean_no_nan'], 
                                           x = "indep_range",
                                           chart_type = "line", 
                                           chart_size = chart_size,
                                           y_num_format = "0.00%", 
                                           line_type = "long_dash",
                                           line_marker = "triangle",
                                           xy_axes_name = (var_desc, "N", "Bad Rate"),
                                           major_gridlines=False,
                                           retChart = True,
                                           y2_axis = True,
                                           append_to_chart = line_chart)

                loc = em.write_combined_chart(ws, 
                                              chart1 = column_chart, 
                                              chart2 = fnl_line_chart, 
                                              chart_size = chart_size, 
                                              skipby = "col", retCellRange="value")
            chart_loc[sample] = loc
        loc1 = chart_loc[sample_list[0]]
        em.curr_row = loc1[2] + em.gap_number
        em.curr_col = loc1[1]
    return ws

add_scr_info 

add_scr_info(em, ws, data, info, scr_info, sample_prefices, wTitle=True)

Add Score Info Comparison

源代码位于： ExcelMaster/Template.py 
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
def add_scr_info(em, ws, data, info, scr_info, sample_prefices, wTitle = True):
    """ Add Score Info Comparison """
    em.gap_number = 0
    title=" "
    if not wTitle:
        title = None
    info_data = data[info].set_index(info[:3])
    info_loc = em.write_dataframe(ws, df=info_data, retCellRange="value", skipby="col", title=title, titleformat="", index = True)

    i = 0
    while i < len(sample_prefices):
        title=sample_prefices[i].upper().strip("_")
        if not wTitle:
            title = None
        tmp = data[[sample_prefices[i] + x for x in scr_info]]
        tmp.columns = [x.replace(sample_prefices[i], "") for x in tmp.columns]
        loc = em.write_dataframe(ws, df=tmp, retCellRange="value", skipby="col", title=title)
        em.set_cell_format(ws, cell_range=[x + 2 if i == 1 else x for i, x in enumerate(loc)], cformat="NUM%.2")
        i += 1

    em.curr_col = info_loc[1]
    em.curr_row = loc[2] + 1
    return (info_loc[1], loc[2] + 1)

add_perf_metrics 

add_perf_metrics(em, ws, data, info, perf_metrics, sample_prefices, wTitle=True)

Add Perf Metrics Comparison

源代码位于： ExcelMaster/Template.py 
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
def add_perf_metrics(em, ws, data, info, perf_metrics, sample_prefices, wTitle = True):
    """ Add Perf Metrics Comparison """
    em.gap_number = 0
    title=" "
    if not wTitle:
        title = None
    info_data = data[info].set_index(info[:3])
    info_loc = em.write_dataframe(ws, df=info_data, retCellRange="value", skipby="col", title=title, titleformat="", index = True)

    i = 0
    while i < len(sample_prefices):
        title=sample_prefices[i].upper().strip("_")
        if not wTitle:
            title = None
        tmp = data[[sample_prefices[i] + x for x in perf_metrics]]
        tmp.columns = [x.replace(sample_prefices[i], "") for x in tmp.columns]
        loc = em.write_dataframe(ws, df=tmp, retCellRange="value", skipby="col", title=title)
        em.set_cell_format(ws, cell_range=[x - 1 if i == 3 else x for i, x in enumerate(loc)], cformat="NUM%.2")
        i += 1

    em.curr_col = info_loc[1]
    em.curr_row = loc[2] + 1
    return (info_loc[1], loc[2] + 1)

add_perf_lift 

add_perf_lift(em, ws, m2_data, m1_data, info, perf_metrics, sample_prefices, wTitle=True)

Add Performance Lift.

源代码位于： ExcelMaster/Template.py 
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
def add_perf_lift(em, ws, m2_data, m1_data, info, perf_metrics, sample_prefices, wTitle = True):
    """  Add Performance Lift. """
    em.gap_number = 0
    title=" "
    if not wTitle:
        title = None

    info_data = m2_data[info]
    info_data[info[0]] = m2_data[info[0]] + " over " + m1_data[info[0]]
    info_data = info_data.set_index(info[:3])
    info_loc = em.write_dataframe(ws, df=info_data, retCellRange="value", skipby="col", title=title, titleformat="", index = True)

    i = 0
    while i < len(sample_prefices):

        title=sample_prefices[i].upper().strip("_")
        if not wTitle:
            title = None

        m2_perf = m2_data[[sample_prefices[i] + x for x in perf_metrics]]
        m2_perf.columns = [x.replace(sample_prefices[i], "") for x in m2_perf.columns]

        m1_perf = m1_data[[sample_prefices[i] + x for x in perf_metrics]]
        m1_perf.columns = [x.replace(sample_prefices[i], "") for x in m1_perf.columns]

        perf_lift = (m2_perf/m1_perf) - 1

        loc = em.write_dataframe(ws, df=perf_lift, retCellRange="value", skipby="col", title=title)
        em.set_cell_format(ws, cell_range=loc, cformat="NUM%.2")
        em.set_data_bar(ws, cell_range=loc)
        i += 1

    em.curr_col = info_loc[1]
    em.curr_row = loc[2] + 1
    return info_loc

get_seg_perf_comparison_report 

get_seg_perf_comparison_report(em, ws, m1_data, bad, sample_prefices, title='Performance Comparison', m2_data=None, perf_metrics=['ks', 'top10_cap', 'top20_cap', 'top40_cap', 'auc'], nbins=100)

Get Segment Perf Eval Report.

源代码位于： ExcelMaster/Template.py 
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
def get_seg_perf_comparison_report(em, ws, m1_data, bad, sample_prefices, 
                                   title = "Performance Comparison",
                                   m2_data = None, 
                                   perf_metrics = ["ks", "top10_cap", "top20_cap", "top40_cap", "auc"], 
                                   nbins=100):
    """ Get Segment Perf Eval Report. """

    metric_cols = [sample + metric for sample in sample_prefices for metric in perf_metrics]

    m1_data = input_validation(m1_data)
    m1_data = convert_perc_str_to_float(m1_data, metric_cols)

    em.gap_number = 0
    em.merge_col(ws, ncols=3, text = title, cformat = "ORANGE_H4")
    em.gap_number = 2
    em.write_text_content(ws, input_text=f"(Gains in {nbins} bins is used.) \n \n")

    info = [f"{sample_prefices[0]}scr_name", "true_bad", "seg_name", "seg_info"]
    scr_info = ["num_of_total", f"num_of_{bad.lower()}", f"rate_of_{bad.lower()}", "mean_score"]
    fnl_loc = add_scr_info(em, ws, m1_data, info, scr_info, sample_prefices)

    if m2_data is not None:
        m2_data = input_validation(m2_data)
        m2_data = convert_perc_str_to_float(m2_data, metric_cols)
        fnl_loc = add_scr_info(em, ws, m2_data, info, scr_info, sample_prefices, False)

    em.curr_col = fnl_loc[0]
    em.curr_row = fnl_loc[1] + 3

    fnl_loc = add_perf_metrics(em, ws, m1_data, info, perf_metrics, sample_prefices)

    if m2_data is not None:
        fnl_loc = add_perf_metrics(em, ws, m2_data, info, perf_metrics, sample_prefices, False)

    em.curr_col = fnl_loc[0]
    em.curr_row = fnl_loc[1] + 3

    if m2_data is not None:
        info_loc = add_perf_lift(em, ws, m2_data, m1_data, info, perf_metrics, sample_prefices)
    return ws

get_means_chart_report 

get_means_chart_report(em, ws, means_rpt, by_class, varlist, class_name=None, stats_list=['N', 'NMISS', 'MIN', 'MEAN', 'MAX'], inc_miss_rate=True, varcol='variable', attr_info=None)

Plot Means Chart and Get Report.

源代码位于： ExcelMaster/Template.py 
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
def get_means_chart_report(em, ws, means_rpt, by_class, varlist, class_name = None, 
                           stats_list = ['N', 'NMISS', 'MIN', 'MEAN', 'MAX'], inc_miss_rate = True,
                           varcol = "variable", attr_info = None):
    """ Plot Means Chart and Get Report. """
    from tqdm import tqdm

    means_rpt = input_validation(means_rpt)

    if class_name is None:
        class_name = by_class

    means_rpt.columns = [x.lower() for x in means_rpt.columns]
    varcol = varcol.lower()
    means_rpt = means_rpt[means_rpt[varcol].isin(varlist)]

    if inc_miss_rate:
        if "missing_rate" not in means_rpt.columns:
            means_rpt["missing_rate"] = means_rpt["nmiss"]/(means_rpt["n"] + means_rpt["nmiss"])

    # em.reset_curr_loc()
    em.gap_number = 2
    em.merge_col(ws, ncols = 5, text="Means Chart by Attribute")

    for var in tqdm(varlist):
        """ By Attribute. """

        if attr_info is not None:
            em.gap_number = 0
            attr_info_table = input_validation(attr_info)
            singe_attr_info = attr_info_table.query(f"{varcol} == '{var.upper()}'")
            em.write_dataframe(ws, df = singe_attr_info, 
                               index = False, 
                               title =f"Information for Attribute {var.upper()}", 
                               skipby="row", retCellRange="value")

        em.gap_number = 2
        example = means_rpt[means_rpt[varcol] == var]
        chart_loc = {}
        for stat in stats_list:
            """ By Statistic. """
            em.write_text_content(worksheet=ws, input_text=f"{stat} ({var}) [[ORANGE_H3]] \n")
            example = example.sort_values([by_class.lower()], ascending = True)

            if inc_miss_rate:
                loc = em.write_duo_chart(ws, 
                                         df = example, 
                                         x = by_class.lower(), 
                                         y1_list=[stat.lower()], 
                                         y2_list = ["missing_rate"],
                                         title = f"{stat.upper()} for Attribute {var}", 
                                         chart_size=(20, 10), 
                                         c1_type="column", 
                                         c2_type="line", 
                                         y2_num_format = "0.00%",
                                         major_gridlines=False, 
                                         xy_axes_name=(class_name, stat, "Missing Rate (%)"), 
                                         skipby="col", 
                                         y1_axis_range=None,
                                         y2_axis_range=None,
                                         retCellRange="value")
            else:
                loc = em.write_chart(ws, 
                                     df = example, 
                                     x = by_class.lower(), 
                                     y_list=[stat.lower()], 
                                     title = f"{stat.upper()} for Attribute {var}", 
                                     chart_size=(20, 10), 
                                     chart_type="column", 
                                     major_gridlines=False, 
                                     xy_axes_name=(class_name, stat), 
                                     skipby="col", 
                                     y_axis_range=None,
                                     retCellRange="value")

            chart_loc[stat] = loc

            em.curr_row = loc[0] - 1

        chart1_loc = chart_loc[stats_list[0]]
        em.curr_row = chart1_loc[2] + em.gap_number
        em.curr_col = chart1_loc[1]

    em.reset_curr_loc()
    return ws

get_grid_boxplot_report 

get_grid_boxplot_report(em, ws, perf_res, hparam_list, metric_list, fontsize=12, figsize=(30, 13), transp_bg=True, color_grp=(20, 1), colored_box=True)

Plot Boxplots of Grid Search Result for Hyperparams.

源代码位于： ExcelMaster/Template.py 
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
def get_grid_boxplot_report(em, ws, perf_res, hparam_list, metric_list, fontsize = 12, figsize = (30, 13), transp_bg = True, color_grp = (20, 1), colored_box = True):
    """ Plot Boxplots of Grid Search Result for Hyperparams.  """

    em.gap_number = 2

    em.merge_col(ws, ncols = 5, text="Boxplot For Grid Search Result")

    chart_loc = {}
    for metric in metric_list:

        em.write_text_content(worksheet=ws, input_text=f"{metric} [[ORANGE_H3]] \n")

        for param in hparam_list:
            loc = em.write_boxplot(ws, 
                             df = perf_res[[param, metric]],
                             x = param,
                             y = metric,
                             y_percentage = True,
                             show_fig = False,
                             colored_box = True,
                             fontsize = fontsize,
                             figsize = figsize,
                             color_grp = color_grp,
                             title=  f"Boxplot for {string_proc(param)}",
                             transp_bg = transp_bg,
                             skipby = "col", 
                             retCellRange = "value")

            chart_loc[param] = loc

        chart1_loc = chart_loc[hparam_list[0]]
        em.curr_row = chart1_loc[2] + em.gap_number
        em.curr_col = chart1_loc[1]

    return ws

get_var_reduct_report 

get_var_reduct_report(em, ws, vr_perf, metric_cols, target_metrics=None, basic_info_text=None, nvars_col='nvars')

Generate Variable Reduction Excel Report.

源代码位于： ExcelMaster/Template.py 
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
def get_var_reduct_report(em, ws, vr_perf, metric_cols, target_metrics = None, basic_info_text = None, nvars_col = "nvars"):
    """ Generate Variable Reduction Excel Report. """

    if target_metrics is None:
        target_metrics = metric_cols

    nvars_col = nvars_col.lower()

    vr_perf = input_validation(vr_perf)
    vr_perf = convert_perc_str_to_float(vr_perf, metric_cols)
    res = get_metrics_shift(vr_perf, [x for x in metric_cols if x in target_metrics])

    shift_cols = [y + "_shift" for y in metric_cols]

    all_metric_cols = metric_cols + shift_cols
    info_table = vr_perf[[x for x in vr_perf.columns if x not in all_metric_cols]]
    metrics_table = vr_perf[[x for x in vr_perf.columns if x in metric_cols]]
    shift_table = vr_perf[[x for x in vr_perf.columns if x in shift_cols]]

    em.write_text_content(ws, input_text="{#} Variable Reduction Report \n")

    if basic_info_text:
        em.write_text_content(ws, input_text=basic_info_text)

    em.gap_number = 0
    info_loc = em.write_dataframe(ws, df=info_table, title = "Model Information", header = True, index = False, retCellRange="value", skipby="col")
    perf_loc = em.write_dataframe(ws, df=metrics_table, title = "Variable Reduction Performance", header = True, index = False, retCellRange="value", skipby="col")
    shift_loc = em.write_dataframe(ws, df=shift_table, title = "Performance Shift", header = True, index = False, retCellRange="value", skipby="row")

    em.set_cell_format(ws, perf_loc, cformat="NUM%.2")
    em.set_cell_format(ws, shift_loc, cformat="NUM%.2")
    em.set_data_bar(ws, shift_loc)

    em.gap_number = 2
    chart_start_loc = (info_loc[2] + em.gap_number, info_loc[1])
    # print(chart_start_loc)
    em.reset_curr_loc(loc = chart_start_loc)

    i = 0
    chart_loc = []
    while i < len(target_metrics):

        metric = target_metrics[i]
        logger.info(metric)

        loc = em.write_duo_chart(worksheet = ws, 
                                 df = res, 
                                 y1_list = [metric], 
                                 y2_list = [metric + '_shift'], 
                                 x = nvars_col,
                                 c1_type = "line", 
                                 c2_type = "line", 
                                 y1_axis_range = None,
                                 y2_axis_range = None, 
                                 title = metric, 
                                 chart_size = (20, 10),
                                 xy_axes_name = ("Nvars", metric, metric + '_shift'),
                                 major_gridlines=False,
                                 retChart = False, 
                                 retCellRange = "value",
                                 skipby = "col",
                                 y1_num_format = "0.00%",
                                 y2_num_format = "0.00%")

        chart_loc.append(loc)
        # print(loc)

        if (i != 0) and (i % 2 == 1):
            reset_loc = (chart_loc[i][2] + em.gap_number, chart_loc[0][1])
            # print(reset_loc)
            em.reset_curr_loc(loc = reset_loc)

        i += 1
    # print(chart_loc)
    return ws

get_grid_search_report 

get_grid_search_report(em, ws, rs_perf, metric_cols, sample_prefices, basic_info_text=None, sortby='hd_auc')

Get Grid Search Report.

源代码位于： ExcelMaster/Template.py 
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
def get_grid_search_report(em, ws, rs_perf, metric_cols, sample_prefices, basic_info_text = None, sortby = "hd_auc"):
    """ Get Grid Search Report. """
    rs_perf = input_validation(rs_perf)
    rs_perf = convert_perc_str_to_float(rs_perf, metric_cols)

    if sortby:
        rs_perf = rs_perf.sort_values([sortby], ascending = False)

    i = 1
    while i <= len(sample_prefices) - 1:
        rs_perf = compute_overfitting_shift(rs_perf, (sample_prefices[0], sample_prefices[i]))
        i += 1

    shift_cols = [x for x in rs_perf.columns if x.endswith("_shift")]

    all_metric_cols = metric_cols + shift_cols
    info_table = rs_perf[[x for x in rs_perf.columns if x not in all_metric_cols]]
    metrics_table = rs_perf[[x for x in rs_perf.columns if x in metric_cols]]
    shift_table = rs_perf[[x for x in rs_perf.columns if x in shift_cols]]

    em.write_text_content(ws, input_text="{#} Grid Search Report \n")

    if basic_info_text:
            em.write_text_content(ws, input_text=basic_info_text)

    em.gap_number = 0
    info_loc = em.write_dataframe(ws, df=info_table, title = "Model Information", header = True, index = False, retCellRange="value", skipby="col")
    perf_loc = em.write_dataframe(ws, df=metrics_table, title = "Grid Search Performance", header = True, index = False, retCellRange="value", skipby="col")
    shift_loc = em.write_dataframe(ws, df=shift_table, title = "Overfitting Performance Shift", header = True, index = False, retCellRange="value", skipby="row")

    em.set_cell_format(ws, perf_loc, cformat="NUM%.2")
    em.set_cell_format(ws, shift_loc, cformat="NUM%.2")
    em.set_data_bar(ws, shift_loc)

    return ws

工具函数 — Utility

Utility

getStartDateofLatestWeek 

getStartDateofLatestWeek(retStr=True)

Date of first day of last week.

源代码位于： ExcelMaster/Utility.py 
15
16
17
18
19
20
21
22
23
24
25
def getStartDateofLatestWeek(retStr=True):
    """ Date of first day of last week. """
    import datetime
    today = datetime.date.today()
    curr_wk = today.strftime("%W")
    d = f"{str(today.year)}-W{curr_wk}"
    r = datetime.datetime.strptime(d + '-1', "%Y-W%W-%w")
    res = (r + datetime.timedelta(days=-1))
    if retStr:
        return res.strftime("%Y-%m-%d")
    return res

getLastCompletedVintage 

getLastCompletedVintage(start_date=None, format='%Y-%m-%d', vintage=False)

Last Completed Vintage

源代码位于： ExcelMaster/Utility.py 
27
28
29
30
31
32
33
34
35
36
37
38
39
def getLastCompletedVintage(start_date = None, format="%Y-%m-%d", vintage=False):
    """ Last Completed Vintage """
    import datetime

    todayDate = datetime.date.today()

    if start_date is not None:
        todayDate = datetime.datetime.strptime(start_date, format).date()    

    lastM = todayDate.replace(day=1) - datetime.timedelta(days=1)
    if vintage:
        return int(lastM.strftime(format)[0:7].replace("-",""))
    return lastM.strftime(format)

vin2quar 

vin2quar(strDate)

String Vintage to Quarter (if compeleted month).

源代码位于： ExcelMaster/Utility.py 
41
42
43
44
45
46
47
48
49
def vin2quar(strDate):
    """ String Vintage to Quarter (if compeleted month). """
    year = int(strDate[:4])
    month = int(strDate[4:6])
    completed_q = [3, 6, 9, 12]
    if month in completed_q:
        q = (month-1)//3 + 1
        return str(year) + "Q" + str(q)
    return strDate

list_files 

list_files(location, pattern)

List all files.

源代码位于： ExcelMaster/Utility.py 
51
52
53
54
55
56
57
58
59
def list_files(location, pattern):
    """ List all files. """
    import re
    res = []
    for root, dirs, files in os.walk(location):
        for file in files:
            if re.search(pattern, file):
                 res.append(file)
    return res

getCurrentDateTime 

getCurrentDateTime(fmt='%Y%m%d%H%M%S')

Get Current DateTime

源代码位于： ExcelMaster/Utility.py 
61
62
63
64
def getCurrentDateTime(fmt = "%Y%m%d%H%M%S"):
    """ Get Current DateTime"""
    import datetime
    return datetime.datetime.now().strftime(fmt)

input_table_proc 

input_table_proc(tbl)

Process Input Table.

源代码位于： ExcelMaster/Utility.py 
66
67
68
69
def input_table_proc(tbl):
    """ Process Input Table. """
    tbl.columns = [x.lower() for x in tbl.columns]
    return tbl

get_file_extension 

get_file_extension(input_path)

Get File Extentsion for a given file Path.

源代码位于： ExcelMaster/Utility.py 
71
72
73
def get_file_extension(input_path):
    """ Get File Extentsion for a given file Path. """
    return os.path.splitext(input_path)[1]

input_validation 

input_validation(x, sep=',')

Input Validation.

源代码位于： ExcelMaster/Utility.py 
75
76
77
78
79
80
81
82
83
84
85
86
87
88
def input_validation(x, sep=","):
    """ Input Validation. """
    import os
    if isinstance(x, str):
        if get_file_extension(x) == ".sas7bdat":
            res = pd.read_sas(x, encoding="latin-1")
        else:
            res = pd.read_csv(x, sep = sep)
        res = input_table_proc(res)
        return res
    elif isinstance(x, pd.DataFrame):
        return input_table_proc(x)
    else:
        raise AttributeError("Only Support csv/sas7bdat Path or Panda DataFrame as Input!!!")

val_input_condition 

val_input_condition(target, condition=('>', 20))

Condition Tuple Validation.

源代码位于： ExcelMaster/Utility.py 
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
def val_input_condition(target, condition = (">", 20)):
    """ Condition Tuple Validation. """
    if isinstance(condition, str):
        return (target == condition)

    else:
        operator = condition[0].strip().lower()
        value = float(condition[1])

        if operator == '>' or operator == 'gt':
            return (target > value)
        elif operator == '<' or operator == 'lt':
            return (target < value)
        elif operator == '=' or operator == 'eq':
            return (target == value)
        elif operator == '>=' or operator == 'gte':
            return (target >= value)
        elif operator == '<=' or operator == 'lte':
            return (target <= value)
        elif operator == '=' or operator == 'eq':
            return (target == value)

tanspose_dataframe 

tanspose_dataframe(df, index_col)

Transpose Pandas DataFrame.

源代码位于： ExcelMaster/Utility.py 
115
116
117
118
def tanspose_dataframe(df, index_col):
    """ Transpose Pandas DataFrame. """
    df = df.set_index(index_col).T.reset_index()
    return df

convert_perc_str_to_float 

convert_perc_str_to_float(df, cols)

Percentage to Float.

源代码位于： ExcelMaster/Utility.py 
120
121
122
123
124
125
def convert_perc_str_to_float(df, cols):
    """ Percentage to Float. """
    for col in cols:
        if str(df[col].dtypes) == 'object':
            df[col] = df[col].str.rstrip('%').astype('float') / 100
    return df

color_hex2rgb 

color_hex2rgb(hex_code)

Convert Color Hex Code to RGB Tuple.

源代码位于： ExcelMaster/Utility.py 
127
128
129
130
131
def color_hex2rgb(hex_code):
    """ Convert Color Hex Code to RGB Tuple. """
    hex_code = hex_code.lower()
    h = hex_code.lstrip('#')
    return tuple(int(h[i:i+2], 16) for i in (0, 2, 4))

get_color_set 

get_color_set(n, start_num=0, step=1, retName=False, lookupName=None)

Return a set of color code without replacement.

源代码位于： ExcelMaster/Utility.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
def get_color_set(n, start_num = 0, step = 1, retName = False, lookupName = None):
    """ Return a set of color code without replacement. """
    import matplotlib.colors as mcolors
    import re

    colors = list(mcolors.XKCD_COLORS.items())
    color_set = {}

    for i in range(start_num, start_num + n * step, step):
        name = colors[i][0].replace("xkcd:", "")
        color = colors[i][1]
        color_set[name] = color

    if lookupName:
        color_set = {}
        i = 0
        for name, color in colors:
            if len(color_set.items()) == n:
                break
            if re.search(lookupName, name):
                color_set[name.replace("xkcd:", "")] = color
            i += 1

    if retName:
        return color_set
    return list(color_set.values())

string_proc 

string_proc(x)

Process a given String.

源代码位于： ExcelMaster/Utility.py 
160
161
162
163
164
165
def string_proc(x):
    """ Process a given String. """
    x_list = x.split("_")
    x_list = [x.strip().capitalize() for x in x_list]
    x = " ".join(x_list)
    return x

convert_to_boxplot_data 

convert_to_boxplot_data(df, x, y, y_percentage=False)

Convert dataframe to boxplot data.

源代码位于： ExcelMaster/Utility.py 
167
168
169
170
171
172
173
174
def convert_to_boxplot_data(df, x, y, y_percentage = False):
    """ Convert dataframe to boxplot data. """
    x_unique_value = df[x].sort_values().unique().tolist()

    box_plot_data = {}
    for v in x_unique_value:
        box_plot_data[v] = [num * 100 if y_percentage else num for num in df[df[x] == v][y].tolist()]
    return box_plot_data

color_input_validation 

color_input_validation(color_grp, val_n)

Perform Color Input Validation.

源代码位于： ExcelMaster/Utility.py 
176
177
178
179
180
181
182
183
184
185
186
187
188
def color_input_validation(color_grp, val_n):
    """ Perform Color Input Validation. """
    if isinstance(color_grp, tuple) and len(color_grp) == 2:
        # Customize colors
        cols = get_color_set(val_n, color_grp[0], color_grp[1], False)
        colors = cols
    elif isinstance(color_grp, str):
        colors = [color_grp] * val_n
    elif (isinstance(color_grp, list)) and (all([isinstance(x, str) for x in color_grp])) and (len(color_grp) == val_n):
        colors = color_grp
    else:
        raise ValueError("Please give valid color_grp: tuple of two numbers, list of color code or a single color code.")
    return colors

get_metric_shift 

get_metric_shift(data, metric_name, nvars_col='nvars')

Calculate Metric Shift for Variable Reduction.

源代码位于： ExcelMaster/Utility.py 
190
191
192
193
194
def get_metric_shift(data, metric_name, nvars_col = "nvars"):
    """ Calculate Metric Shift for Variable Reduction. """
    metric_lift = (data[metric_name] - data[metric_name].shift(1))
    nvars_reduced = (data[nvars_col] - data[nvars_col].shift(1))
    return (metric_lift / nvars_reduced).fillna(0)

get_metrics_shift 

get_metrics_shift(data, metric_cols)

Get Shift for List of Metrics.

源代码位于： ExcelMaster/Utility.py 
196
197
198
199
200
201
def get_metrics_shift(data, metric_cols):
    """ Get Shift for List of Metrics."""
    for metric in metric_cols:
        if metric.startswith(tuple(metric_cols)):
            data[metric+"_shift"] = get_metric_shift(data, metric)
    return data

compute_overfitting_shift 

compute_overfitting_shift(data, sample_prefix)

Calculate Overfitting Performance Shift.

源代码位于： ExcelMaster/Utility.py 
203
204
205
206
207
208
209
210
211
212
213
def compute_overfitting_shift(data, sample_prefix):
    """ Calculate Overfitting Performance Shift. """
    b_metrics = [x for x in data.columns if x.startswith(sample_prefix[0])]
    o_metrics = [x for x in data.columns if x.startswith(sample_prefix[1])]

    if len(b_metrics) == len(o_metrics):
        for b_metric, o_metric in zip(b_metrics, o_metrics):
            data[o_metric+"_shift"] = data[o_metric].div(data[b_metric]) - 1
        return data

    raise ValueError("The lengths of metrics between two samples are the the same in the given dataset!")

proc_psi_raw_report 

proc_psi_raw_report(psi_raw_table, psi_title, keep_list=None, varname='variable', upper=True)

Processing Raw PSI Report generated from Takecopter.

源代码位于： ExcelMaster/Utility.py 
215
216
217
218
219
220
221
222
223
224
225
def proc_psi_raw_report(psi_raw_table, psi_title, keep_list = None, varname = "variable", upper=True):
    """ Processing Raw PSI Report generated from Takecopter. """
    psi_table = input_validation(psi_raw_table)
    psi_table = psi_table.rename(columns={"var_for_psi":varname})
    psi_table = psi_table.set_index(varname)
    if upper:
        psi_table.columns = [x.upper() for x in psi_table.columns]
    psi_table.columns = [[psi_title]*len(psi_table.columns),psi_table.columns]
    if keep_list:
        psi_table = psi_table[[(psi_title, x) for x in keep_list]]
    return psi_table

get_mean_risk 

get_mean_risk(bivar_single_attr, value_range_col=['min_indep', 'max_indep'], dep_col='dep')

get average risk

源代码位于： ExcelMaster/Utility.py 
227
228
229
230
231
232
233
def get_mean_risk(bivar_single_attr, value_range_col = ['min_indep', 'max_indep'], dep_col = "dep"):
    """get average risk"""
    mean_wo_nan = bivar_single_attr.dropna(how = "all", subset=value_range_col)[dep_col].mean()
    mean_w_na = bivar_single_attr[dep_col].mean()
    bivar_single_attr["mean"] = mean_w_na
    bivar_single_attr["mean_no_nan"] = mean_wo_nan
    return bivar_single_attr