kivi 0.2.4__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (89) hide show
  1. kivi-0.2.4/PKG-INFO +19 -0
  2. kivi-0.2.4/README.md +6 -0
  3. kivi-0.2.4/kivi/BucketsAnalysis/BucketsUtils.py +83 -0
  4. kivi-0.2.4/kivi/BucketsAnalysis/CSI.py +105 -0
  5. kivi-0.2.4/kivi/BucketsAnalysis/KS.py +374 -0
  6. kivi-0.2.4/kivi/BucketsAnalysis/PSI.py +124 -0
  7. kivi-0.2.4/kivi/BucketsAnalysis/__init__.py +3 -0
  8. kivi-0.2.4/kivi/Card/Calibration.py +138 -0
  9. kivi-0.2.4/kivi/Card/MasterScale.py +120 -0
  10. kivi-0.2.4/kivi/Card/ScoreCard.py +99 -0
  11. kivi-0.2.4/kivi/Card/__init__.py +6 -0
  12. kivi-0.2.4/kivi/Card/card_eval.py +110 -0
  13. kivi-0.2.4/kivi/Card/card_rant.py +15 -0
  14. kivi-0.2.4/kivi/Card/card_score.py +87 -0
  15. kivi-0.2.4/kivi/Card/utils.py +26 -0
  16. kivi-0.2.4/kivi/Dataset/Dataset.py +53 -0
  17. kivi-0.2.4/kivi/Dataset/__init__.py +1 -0
  18. kivi-0.2.4/kivi/Dataset/bank.xlsx +0 -0
  19. kivi-0.2.4/kivi/Dataset/crime_data.csv +52 -0
  20. kivi-0.2.4/kivi/DesStatistic/CategoryData.py +71 -0
  21. kivi-0.2.4/kivi/DesStatistic/DefaultAnalysis.py +290 -0
  22. kivi-0.2.4/kivi/DesStatistic/__init__.py +6 -0
  23. kivi-0.2.4/kivi/FeatureAnalysis/Corr.py +35 -0
  24. kivi-0.2.4/kivi/FeatureAnalysis/FeatureSelect.py +27 -0
  25. kivi-0.2.4/kivi/FeatureAnalysis/Univariate.py +122 -0
  26. kivi-0.2.4/kivi/FeatureAnalysis/VIF.py +140 -0
  27. kivi-0.2.4/kivi/FeatureAnalysis/__init__.py +3 -0
  28. kivi-0.2.4/kivi/FeatureTools/FeatureTools.py +352 -0
  29. kivi-0.2.4/kivi/FeatureTools/FeatureToolsV2.py +255 -0
  30. kivi-0.2.4/kivi/FeatureTools/Scale.py +21 -0
  31. kivi-0.2.4/kivi/FeatureTools/__init__.py +2 -0
  32. kivi-0.2.4/kivi/Model/Apriori.py +135 -0
  33. kivi-0.2.4/kivi/Model/Lasso.py +97 -0
  34. kivi-0.2.4/kivi/Model/Linear.py +359 -0
  35. kivi-0.2.4/kivi/Model/LogisticRegression.py +163 -0
  36. kivi-0.2.4/kivi/Model/Ridge.py +61 -0
  37. kivi-0.2.4/kivi/Model/Tree.py +77 -0
  38. kivi-0.2.4/kivi/Model/__init__.py +9 -0
  39. kivi-0.2.4/kivi/Model/simtext.py +102 -0
  40. kivi-0.2.4/kivi/ModelEval/ModelEval.py +248 -0
  41. kivi-0.2.4/kivi/ModelEval/__init__.py +1 -0
  42. kivi-0.2.4/kivi/ModelTools/Calibration.py +244 -0
  43. kivi-0.2.4/kivi/ModelTools/Metrics.py +170 -0
  44. kivi-0.2.4/kivi/ModelTools/Sampling.py +53 -0
  45. kivi-0.2.4/kivi/ModelTools/__init__.py +4 -0
  46. kivi-0.2.4/kivi/Plot/Heatmap.py +52 -0
  47. kivi-0.2.4/kivi/Plot/__init__.py +0 -0
  48. kivi-0.2.4/kivi/PortfolioAnalysis/PortfolioAnalysis.py +269 -0
  49. kivi-0.2.4/kivi/PortfolioAnalysis/__init__.py +1 -0
  50. kivi-0.2.4/kivi/SQLengine/SQLengine.py +152 -0
  51. kivi-0.2.4/kivi/SQLengine/__init__.py +6 -0
  52. kivi-0.2.4/kivi/SparkSupport/SparkSupport.py +530 -0
  53. kivi-0.2.4/kivi/SparkSupport/__init__.py +4 -0
  54. kivi-0.2.4/kivi/Stepwise/Stepwise.py +123 -0
  55. kivi-0.2.4/kivi/Stepwise/__init__.py +1 -0
  56. kivi-0.2.4/kivi/Utils/BeautyExcel.py +193 -0
  57. kivi-0.2.4/kivi/Utils/Bins.py +28 -0
  58. kivi-0.2.4/kivi/Utils/Operator.py +187 -0
  59. kivi-0.2.4/kivi/Utils/Typing.py +8 -0
  60. kivi-0.2.4/kivi/Utils/__init__.py +8 -0
  61. kivi-0.2.4/kivi/Utils/encrypt.py +61 -0
  62. kivi-0.2.4/kivi/Utils/markdown.py +56 -0
  63. kivi-0.2.4/kivi/Utils/utils.py +226 -0
  64. kivi-0.2.4/kivi/Utils/utils_date.py +75 -0
  65. kivi-0.2.4/kivi/WOE/FixWOE.py +232 -0
  66. kivi-0.2.4/kivi/WOE/TransWOEScore.py +161 -0
  67. kivi-0.2.4/kivi/WOE/WOE.py +360 -0
  68. kivi-0.2.4/kivi/WOE/WOEKmeans.py +60 -0
  69. kivi-0.2.4/kivi/WOE/WoeBatch.py +225 -0
  70. kivi-0.2.4/kivi/WOE/WoeCategory.py +38 -0
  71. kivi-0.2.4/kivi/WOE/WoeChi2.py +251 -0
  72. kivi-0.2.4/kivi/WOE/WoeCutOffPoint.py +43 -0
  73. kivi-0.2.4/kivi/WOE/WoeDistance.py +39 -0
  74. kivi-0.2.4/kivi/WOE/WoeFrequency.py +37 -0
  75. kivi-0.2.4/kivi/WOE/WoeKSMerge.py +90 -0
  76. kivi-0.2.4/kivi/WOE/WoePearson.py +153 -0
  77. kivi-0.2.4/kivi/WOE/WoeTree.py +76 -0
  78. kivi-0.2.4/kivi/WOE/__init__.py +13 -0
  79. kivi-0.2.4/kivi/__init__.py +5 -0
  80. kivi-0.2.4/kivi/fake_data/__init__.py +2 -0
  81. kivi-0.2.4/kivi/fake_data/fake_data.py +86 -0
  82. kivi-0.2.4/kivi/fake_data/fake_data_config.py +20 -0
  83. kivi-0.2.4/kivi.egg-info/PKG-INFO +19 -0
  84. kivi-0.2.4/kivi.egg-info/SOURCES.txt +87 -0
  85. kivi-0.2.4/kivi.egg-info/dependency_links.txt +1 -0
  86. kivi-0.2.4/kivi.egg-info/requires.txt +8 -0
  87. kivi-0.2.4/kivi.egg-info/top_level.txt +1 -0
  88. kivi-0.2.4/setup.cfg +4 -0
  89. kivi-0.2.4/setup.py +45 -0
kivi-0.2.4/PKG-INFO ADDED
@@ -0,0 +1,19 @@
1
+ Metadata-Version: 2.1
2
+ Name: kivi
3
+ Version: 0.2.4
4
+ Summary: A Bank Risk Manager
5
+ Home-page: https://github.com/Risk-KIVI/kivi
6
+ Author: chensy.cao
7
+ Author-email: chensy.cao@foxmail.com
8
+ Classifier: Programming Language :: Python :: 3
9
+ Classifier: License :: OSI Approved :: MIT License
10
+ Classifier: Operating System :: OS Independent
11
+ Requires-Python: >=3.8
12
+ Description-Content-Type: text/markdown
13
+
14
+ # kivi
15
+
16
+ **Author: Chensy**
17
+ **Email: chensy.cao@foxmail.com**
18
+
19
+ ----
kivi-0.2.4/README.md ADDED
@@ -0,0 +1,6 @@
1
+ # kivi
2
+
3
+ **Author: Chensy**
4
+ **Email: chensy.cao@foxmail.com**
5
+
6
+ ----
@@ -0,0 +1,83 @@
1
+ import numpy as np
2
+ import pandas as pd
3
+ from pyspark.sql import functions as F
4
+
5
+ __all__ = [
6
+ "quantile",
7
+ "getQuantiles",
8
+ "psi",
9
+ "csi",
10
+ ]
11
+
12
+
13
+
14
+ def quantile(col: str, percent=0.5):
15
+ """
16
+ 描述:分位数计算
17
+
18
+ 参数:
19
+ :param col: 字段名称
20
+ :param percent: 分位点
21
+ :return : pyspark.sql.functions
22
+ """
23
+ return F.expr(f'percentile_approx({col}, {percent})')
24
+
25
+ def getQuantiles(df, column_name, ranges=np.linspace(0, 1, 11))->list:
26
+ """
27
+ 描述:获取字段的分位数点。
28
+
29
+ 参数:
30
+ :param df:
31
+ :param column_name:
32
+ :param ranges:
33
+ :return : 分位数值 List
34
+
35
+ 示例:获取多个字段的多个分位点
36
+ >>> quant_val_list = [getQuantiles(df, col) for col in cols]
37
+ >>> pd.DataFrame(dict(zip(cols, quant_val_list)), index=np.linspace(0, 1, 11)).T
38
+ """
39
+ quantiles = [quantile(column_name, i).alias(f'i') for i in ranges]
40
+ return df.agg(*quantiles).toPandas().values.flatten().tolist()
41
+
42
+
43
+ def psi(df_buckets, ex_name='Expected', ac_name='Actual', fill_bin=True):
44
+ """
45
+
46
+ :param df_buckets:
47
+ :param ex_name:
48
+ :param ac_name:
49
+ :return:
50
+ """
51
+ if fill_bin:
52
+ if 0 in df_buckets[ex_name].tolist():
53
+ df_buckets[ex_name] += 0.5
54
+ if 0 in df_buckets[ac_name].tolist():
55
+ df_buckets[ac_name] += 0.5
56
+
57
+ df_buckets['Expected_percentage'] = df_buckets[ex_name] / df_buckets[ex_name].sum()
58
+ df_buckets['Actual_percentage'] = df_buckets[ac_name] / df_buckets[ac_name].sum()
59
+ df_buckets['A-E'] = df_buckets.Actual_percentage - df_buckets.Expected_percentage
60
+ df_buckets['A/E'] = df_buckets.Actual_percentage / df_buckets.Expected_percentage
61
+ df_buckets['ln(A/E)'] = np.log(df_buckets['A/E'])
62
+ df_buckets['psi_val'] = df_buckets['A-E'] * df_buckets['ln(A/E)']
63
+ df_buckets['psi'] = df_buckets['psi_val'].sum()
64
+ return df_buckets
65
+
66
+
67
+ def csi(df_buckets, ex_name='Expected', ac_name='Actual', fill_bin=True):
68
+ """
69
+ Des: 计算CSI的核心函数
70
+ :param df_buckets: 明细表
71
+ :return: 明细表以及CSI值 df_buckets, csi
72
+ """
73
+
74
+ df_buckets['Expected_percentage'] = df_buckets.Expected / df_buckets.Expected.sum()
75
+ df_buckets['Actual_percentage'] = df_buckets.Actual / df_buckets.Actual.sum()
76
+ df_buckets['A-E'] = df_buckets.Actual_percentage - df_buckets.Expected_percentage
77
+ if len(df_buckets) != len(self.score):
78
+ raise Exception(TypeError, 'Score len error!')
79
+ df_buckets['score'] = self.score
80
+ df_buckets['index'] = df_buckets['A-E'] * self.score
81
+ df_buckets['csi'] = df_buckets['index'].sum()
82
+ return df_buckets
83
+
@@ -0,0 +1,105 @@
1
+ from ..Utils.utils import pd
2
+ from ..Utils.Bins import Bins
3
+
4
+
5
+ class CSI(Bins):
6
+ def __init__(self, score=None):
7
+ """
8
+ Des: 计算CSI
9
+ :param score: 分箱分数
10
+ :param margin: cutoff point 左右填充预留边界
11
+ """
12
+ super(CSI, self).__init__()
13
+ self.score = score
14
+
15
+ def _csi(self, res):
16
+ """
17
+ Des: 计算CSI的核心函数
18
+ :param res: 明细表
19
+ :return: 明细表以及CSI值 res, csi
20
+ """
21
+
22
+ res['Expected_percentage'] = res.Expected / res.Expected.sum()
23
+ res['Actual_percentage'] = res.Actual / res.Actual.sum()
24
+ res['A-E'] = res.Actual_percentage - res.Expected_percentage
25
+ if len(res) != len(self.score):
26
+ raise Exception(TypeError, 'Score len error!')
27
+ res['score'] = self.score
28
+ res['index'] = res['A-E'] * self.score
29
+ csi = res['index'].sum()
30
+ return res, csi
31
+
32
+ def Continue(self, expected, actual, bins=10, binType='distance', cutPoint=None):
33
+ """
34
+ Des: 连续型变量的CSI指标
35
+ :param expected: 预期分布
36
+ :param actual: 实际分布
37
+ :param bins: 分箱数目
38
+ :param binType: 分箱类型 'distance'等距 or 'frequency'等频 or 'customize'自定义
39
+ :param csvName: 保存CSV Name, 默认不保存
40
+ :return: 明细表以及CSI值 res, CSI
41
+ """
42
+ expected.dropna(inplace=True)
43
+ actual.dropna(inplace=True)
44
+
45
+ expectedMax = expected.max()
46
+ expectedMin = expected.min()
47
+ actualMax = actual.max()
48
+ actualMin = actual.min()
49
+
50
+ if not pd.api.types.is_numeric_dtype(expected):
51
+ raise Exception(TypeError, 'expected must be numeric!')
52
+
53
+ if not pd.api.types.is_numeric_dtype(actual):
54
+ raise Exception(TypeError, 'actual must be numeric!')
55
+
56
+ if (expectedMax == expectedMin) or (actualMax == actualMin):
57
+ raise Exception()
58
+
59
+ if (expectedMin > actualMin) or (expectedMax < actualMax):
60
+ raise Exception()
61
+
62
+ if binType == 'distance':
63
+ cutoffPoint = self._cutoffPoint(
64
+ bins=bins, min=expectedMin, max=expectedMax)
65
+ elif binType == 'frequency':
66
+ cutoffPoint = self._cutoffPoint(
67
+ bins=bins, percent=True, expected=expected)
68
+ elif binType == 'customize' and cutPoint:
69
+ cutoffPoint = cutPoint
70
+ else:
71
+ raise Exception(TypeError, '分箱错误!')
72
+
73
+ res = pd.DataFrame({
74
+ 'Expected': pd.cut(expected, cutoffPoint).value_counts(sort=False),
75
+ 'Actual': pd.cut(actual, cutoffPoint).value_counts(sort=False),
76
+ },)
77
+
78
+ return self._csi(res)
79
+
80
+ def Category(self, expected, actual):
81
+ """
82
+ Des: 类别型变量的CSI
83
+ :param expected:
84
+ :param actual:
85
+ :return: 明细表以及CSI值 res, CSI
86
+ """
87
+ if (not pd.api.types.is_string_dtype(expected)) or (not pd.api.types.is_object_dtype(expected)):
88
+ raise Exception(TypeError, 'expected must be string or object!')
89
+ if (not pd.api.types.is_string_dtype(actual)) or (not pd.api.types.is_object_dtype(actual)):
90
+ raise Exception(TypeError, 'actual must be string or object!')
91
+
92
+ expected.dropna(inplace=True)
93
+ actual.dropna(inplace=True)
94
+
95
+ expectedGroup = expected.value_counts(sort=False)
96
+ actualGroup = actual.value_counts(sort=False)
97
+
98
+ res = pd.merge(
99
+ pd.DataFrame({'category': expectedGroup.index, 'Expected': expectedGroup.values}),
100
+ pd.DataFrame({'category': actualGroup.index, 'Actual': actualGroup.values}),
101
+ on='category',
102
+ how='outer',)
103
+
104
+ self.res, self.csi = self._csi(res)
105
+ return self.res, self.csi
@@ -0,0 +1,374 @@
1
+ import numpy as np
2
+ from ..Utils.utils import pd, saveCsv
3
+ from ..Utils.Bins import Bins
4
+
5
+
6
+ class KS(Bins):
7
+
8
+ def __init__(self, csvName=None, imageName=None, jupyterNotebook=True):
9
+ """
10
+ Des: KS 初始化
11
+ :param csvName: 保存csv计算过程文件
12
+ :param imageName: 保存ks图像
13
+ :param jupyterNotebook 是否显示在JupyterNotebook中
14
+ """
15
+ super(KS, self).__init__()
16
+ self.csvName = csvName
17
+ self.imageName = imageName
18
+ self.jupyterNotebook = jupyterNotebook
19
+
20
+ def _ks(self, variables, target, **kwargs):
21
+ """
22
+ Des: KS 方法中的内部核心计算函数
23
+ :param variables:
24
+ :param target:
25
+ :param kwargs:
26
+ :return:
27
+ """
28
+
29
+ kwargs.setdefault('category', False)
30
+
31
+ from numpy import abs
32
+ total = len(target)
33
+ total_bad = target.sum()
34
+
35
+ if kwargs['category']:
36
+ bucket = DataFrame({
37
+ 'variables': variables,
38
+ 'target': target,
39
+ }).groupby('variables', as_index=True)
40
+ else:
41
+ bucket = DataFrame({
42
+ 'variables': variables,
43
+ 'target': target,
44
+ 'Bucket': cut(variables, self.cutoffPoint, include_lowest=True)
45
+ }).groupby('Bucket', as_index=True)
46
+
47
+ res = DataFrame({
48
+ 'min_bin': bucket.variables.min(),
49
+ 'max_bin': bucket.variables.max(),
50
+ 'bad': bucket.target.sum(),
51
+ 'total': bucket.target.count(),
52
+ })
53
+
54
+ res['good'] = res['total'] - res['bad']
55
+ res['bad_rate'] = res['bad'] / res['total'] # 每个箱体中好样本所占总样本数的比例
56
+ res['total_rate'] = res['total'] / total
57
+ res['cum_bad_rate'] = res.bad.cumsum() / total_bad
58
+ res['cum_good_rate'] = res.good.cumsum() / (total - total_bad)
59
+ res['ks'] = abs(res.cum_bad_rate - res.cum_good_rate)
60
+ res = res[[
61
+ 'min_bin', 'max_bin', 'total',
62
+ 'total_rate', 'good', 'bad',
63
+ 'bad_rate', 'cum_bad_rate',
64
+ 'cum_good_rate', 'ks']]
65
+ return res, res.ks.max()
66
+
67
+ def Continue(
68
+ self,
69
+ variables: Series,
70
+ target: Series,
71
+ bins=10,
72
+ binType='distance'):
73
+ """
74
+ Des: 连续变量的KS值计算
75
+ :param variables: 连续变量
76
+ :param target: target
77
+ :param bins: 分箱数目
78
+ :param binType: 分箱方式: 等距'distance', 等频'frequency'
79
+ :return: res, ks
80
+ """
81
+
82
+ variables.dropna(inplace=True)
83
+ target.dropna(inplace=True)
84
+
85
+ variablesMin = variables.min()
86
+ variablesMax = variables.max()
87
+
88
+ if not pd.api.types.is_numeric_dtype(variables):
89
+ raise Exception(TypeError, 'variables must be numeric!')
90
+
91
+ if not pd.api.types.is_numeric_dtype(target):
92
+ raise Exception(TypeError, 'target must be numeric!')
93
+
94
+ if variablesMax == variablesMin:
95
+ raise Exception()
96
+
97
+ if binType == 'distance':
98
+ self.cutoffPoint = self._cutoffPoint(
99
+ bins=bins, min=variablesMin, max=variablesMax)
100
+ if binType == 'frequency':
101
+ self.cutoffPoint = self._cutoffPoint(
102
+ bins=bins, percent=True, expected=variables)
103
+
104
+ self.res, self.ks = self._ks(variables, target)
105
+
106
+ if self.csvName:
107
+ saveCsv(self.res, self.csvName)
108
+ return self.ks
109
+ else:
110
+ return self.res, self.ks
111
+
112
+ def Category(self, variables: Series, target: Series):
113
+ """
114
+ Des: 对于类别型变量的KS值计算
115
+ :param variables: 类别变量
116
+ :param target: target
117
+ :return: res, ks
118
+ """
119
+
120
+ variables = variables.dropna()
121
+ target = target.dropna()
122
+
123
+ if (not is_string_dtype(variables)) or (not is_object_dtype(variables)):
124
+ raise Exception(TypeError, 'variables must be string or object!')
125
+ if not is_numeric_dtype(target):
126
+ raise Exception(TypeError, 'target must be numeric!')
127
+
128
+ self.res, self.ks = self._ks(variables, target, category=True)
129
+
130
+ if self.csvName:
131
+ saveCsv(self.res, self.csvName)
132
+ return self.ks
133
+ else:
134
+ return self.res, self.ks
135
+
136
+ def KSPlot(self, **kwargs):
137
+ """
138
+ Des: 绘制 KS 曲线
139
+ :param kwargs:
140
+ # 图像样式
141
+ style[str] = 'seaborn',
142
+ # 宽,高
143
+ figsize[tuple] = (9, 5),
144
+ # 分辨率
145
+ dpi[int] = 150,
146
+ # x 轴名称
147
+ x_label[str] = 'Bucket',
148
+ # label 字体大小
149
+ labelfontsize[int] = 10,
150
+ # tick 字体大小
151
+ tickfontsize[int] = 8,
152
+ # title 字体大小
153
+ titlefontsize[int] = 12,
154
+ :return: plt.show() or None
155
+ """
156
+ from numpy import argmax
157
+
158
+ kwargs.setdefault('style', 'seaborn')
159
+ kwargs.setdefault('figsize', (9, 5))
160
+ kwargs.setdefault('dpi', 150)
161
+ kwargs.setdefault('labelfontsize', 10)
162
+ kwargs.setdefault('tickfontsize', 8)
163
+ kwargs.setdefault('titlefontsize', 12)
164
+ kwargs.setdefault('x_label', 'Bucket')
165
+
166
+ markLineData = self.res[self.res.ks == self.ks]
167
+
168
+ cumGood, cumBad = float(
169
+ markLineData['cum_good_rate']), float(
170
+ markLineData['cum_bad_rate'])
171
+
172
+ if isinstance(self.res.min_bin.to_list()[0], int):
173
+ group = self.res.min_bin.astype(
174
+ str) + '-' + self.res.max_bin.astype(str)
175
+ ksBinMin, ksBinMax = int(
176
+ markLineData['min_bin']), int(
177
+ markLineData['max_bin'])
178
+
179
+ if isinstance(self.res.min_bin.to_list()[0], float):
180
+ group = self.res.min_bin.round(2).astype(
181
+ str) + '-' + self.res.max_bin.round(2).astype(str)
182
+ ksBinMin, ksBinMax = float(
183
+ markLineData['min_bin'].round(2)), float(
184
+ markLineData['max_bin'].round(2))
185
+
186
+ bucket = '[' + str(ksBinMin) + ', ' + str(ksBinMax) + ']'
187
+
188
+ import matplotlib.pyplot as plt
189
+ plt.style.use(kwargs.get('style'))
190
+ fig, axs = plt.subplots(
191
+ figsize=kwargs.get('figsize'),
192
+ dpi=kwargs.get('dpi')
193
+ )
194
+ axs.plot(
195
+ group,
196
+ self.res.ks * 100,
197
+ marker='o',
198
+ linewidth=3,
199
+ c='tab:blue')
200
+ axs.plot(
201
+ group,
202
+ self.res.cum_good_rate *
203
+ 100,
204
+ marker='o',
205
+ linewidth=3,
206
+ c='tab:green')
207
+ axs.plot(
208
+ group,
209
+ self.res.cum_bad_rate *
210
+ 100,
211
+ marker='o',
212
+ linewidth=3,
213
+ c='tab:red')
214
+
215
+ # 参考线
216
+ axs.axvline(x=argmax(self.res.ks.to_list()), linestyle='--', c='gray')
217
+ axs.axhline(y=self.ks * 100, linestyle='--', c='tab:blue')
218
+ axs.axhline(y=cumGood * 100, linestyle='--', c='tab:green')
219
+ axs.axhline(y=cumBad * 100, linestyle='--', c='tab:red')
220
+
221
+ axs.set_title(
222
+ f'KS = {self.ks * 100: .2f}% at bucket {bucket}',
223
+ fontsize=kwargs.get('titlefontsize'))
224
+ axs.legend(fontsize=kwargs.get('tickfontsize'))
225
+
226
+ axs.set_xlabel(
227
+ kwargs.get('x_label'),
228
+ fontsize=kwargs.get('labelfontsize'),
229
+ )
230
+ axs.set_ylabel(
231
+ r'$Rate(\%)$',
232
+ fontsize=kwargs.get('labelfontsize'),)
233
+ axs.tick_params(axis="x", labelsize=kwargs.get('tickfontsize'))
234
+ axs.tick_params(axis="y", labelsize=kwargs.get('tickfontsize'))
235
+ axs.grid(True)
236
+ return plt.show()
237
+
238
+ def KSValue(self, variables, target):
239
+ """
240
+ Des: 计算KS值,计算KS-test的P-value
241
+ :param variables:
242
+ :param target:
243
+ :return: ks_value, p_value
244
+ """
245
+ from scipy.stats import ks_2samp
246
+ get_ks = lambda variables, target: ks_2samp(variables[target == 1], variables[target == 0])
247
+ ks_value, p_value = get_ks(variables, target)
248
+ return ks_value, p_value
249
+
250
+ def ROCPlot(self, **kwargs):
251
+ """
252
+ Des: 根据KS计算ROC曲线
253
+ :param kwargs: 图像参数['style', 'figsize', 'dpi', 'labelfontsize', title, 'x_label', 'y_label'……]
254
+ :return: None
255
+ """
256
+
257
+ kwargs.setdefault('style', 'seaborn')
258
+ kwargs.setdefault('figsize', (9, 5))
259
+ kwargs.setdefault('dpi', 150)
260
+ kwargs.setdefault('labelfontsize', 10)
261
+ kwargs.setdefault('tickfontsize', 8)
262
+ kwargs.setdefault('titlefontsize', 12)
263
+ kwargs.setdefault('x_label', 'False Positive Rate')
264
+ kwargs.setdefault('y_label', 'True Positive Rate')
265
+ kwargs.setdefault('title', 'Receiver operating characteristic')
266
+
267
+ import matplotlib.pyplot as plt
268
+ from numpy import abs, argmax
269
+ plt.style.use(kwargs.get('style'))
270
+ fig, axs = plt.subplots(
271
+ figsize=kwargs.get('figsize'),
272
+ dpi=kwargs.get('dpi')
273
+ )
274
+
275
+ FPR = self.res.cum_good_rate.tolist()
276
+ TPR = self.res.cum_bad_rate.tolist()
277
+ FPR.insert(0, 0)
278
+ TPR.insert(0, 0)
279
+ axs.plot(FPR, TPR, marker='o',
280
+ linewidth=3,
281
+ c='tab:green',
282
+ label='$ROC\ curve$',
283
+ )
284
+
285
+ axs.plot([0, 1], [0, 1], linestyle='--', c='gray')
286
+
287
+ maxIndex = argmax(abs(self.res.cum_bad_rate -
288
+ self.res.cum_good_rate).tolist())
289
+ axs.scatter(
290
+ self.res.cum_good_rate[maxIndex],
291
+ self.res.cum_bad_rate[maxIndex],
292
+ alpha=0.8,
293
+ marker='*',
294
+ s=100,
295
+ color='tab:red',
296
+ label='$KS\ max\|cum\_bad\_rate-cum\_good\_rate\|$'
297
+ ).set_zorder(10)
298
+
299
+ axs.set_title(
300
+ kwargs.get('title'),
301
+ fontsize=kwargs.get('titlefontsize'))
302
+ axs.legend(fontsize=kwargs.get('tickfontsize'))
303
+
304
+ axs.set_xlabel(
305
+ kwargs.get('x_label'),
306
+ fontsize=kwargs.get('labelfontsize'),
307
+ )
308
+ axs.set_ylabel(
309
+ kwargs.get('y_label'),
310
+ fontsize=kwargs.get('labelfontsize'),
311
+ )
312
+
313
+ if self.imageName:
314
+ if not os.path.exists('img'):
315
+ os.mkdir('img')
316
+ plt.savefig(f'./img/{self.imageName}_roc.png', )
317
+ return None
318
+ else:
319
+ return plt.show()
320
+
321
+ def Distribution(self, data: dict, **kwargs):
322
+ """
323
+ Des: 绘制多个样本的分布情况
324
+ :param data: 数据
325
+ :param kwargs: 图像参数['style', 'figsize', 'dpi', 'labelfontsize', title, 'x_label', 'y_label'……]
326
+ :return: plt.plot
327
+ """
328
+
329
+ kwargs.setdefault('style', 'seaborn')
330
+ kwargs.setdefault('figsize', (9, 5))
331
+ kwargs.setdefault('dpi', 150)
332
+ kwargs.setdefault('labelfontsize', 10)
333
+ kwargs.setdefault('tickfontsize', 8)
334
+ kwargs.setdefault('titlefontsize', 12)
335
+ kwargs.setdefault('x_label', 'Variable')
336
+ kwargs.setdefault('y_label', 'Frequency')
337
+ kwargs.setdefault('title', 'Distribution')
338
+
339
+ import seaborn as sns
340
+ import matplotlib.pyplot as plt
341
+
342
+ plt.style.use(kwargs.get('style'))
343
+
344
+ fig, axs = plt.subplots(
345
+ figsize=kwargs.get('figsize'),
346
+ dpi=kwargs.get('dpi')
347
+ )
348
+
349
+ with sns.color_palette("muted", n_colors=len(data)):
350
+ for name, item in data.items():
351
+ sns.distplot(item, label=name)
352
+
353
+ axs.legend()
354
+
355
+ axs.set_title(
356
+ kwargs.get('title'),
357
+ fontsize=kwargs.get('titlefontsize'))
358
+
359
+ axs.set_xlabel(
360
+ kwargs.get('x_label'),
361
+ fontsize=kwargs.get('labelfontsize'),
362
+ )
363
+ axs.set_ylabel(
364
+ kwargs.get('y_label'),
365
+ fontsize=kwargs.get('labelfontsize'),
366
+ )
367
+
368
+ if self.imageName:
369
+ if not os.path.exists('img'):
370
+ os.mkdir('img')
371
+ plt.savefig(f'./img/{self.imageName}_distribution.png', )
372
+ return None
373
+ else:
374
+ return plt.show()