├── README.md
├── baseline.ipynb
├── 第一、二问集成学习算法.ipynb
├── 第一问信用评级的描述性统计.ipynb
├── 第一问所有特征.csv
├── 第一问风险违约率求解.ipynb
├── 第一问：作废发票计算.ipynb
└── 论文.pdf


/README.md:
--------------------------------------------------------------------------------
 1 | # 2020-CMCM-C
 2 | 2020年数学建模国赛C题国一优秀论文——编号C227：银行对中小微企业的信贷决策分析
 3 | 
 4 | # 比赛的代码
 5 | 这个项目包含了C227这篇论文的代码和特征工程之后的数据集，特征工程的全部代码我找不到了，所以我放上了第一问的csv文件，在new_code文件夹下。
 6 | 论文中有比赛期间我们的全部代码，***但是我不确定有没有问题hhh***
 7 | 模型训练部分的代码其实有些问题，比如我们用了全部数据集做评估，而不是测试集。
 8 | 
 9 | # 更新后的代码（baseline.ipynb）
10 | baseline中的代码是更改之后的代码，我尝试使用了SMOTETomek（一种过采样+欠采样）的方法，
11 | Stacking融合之后的AUC还是可以达到***0.98***的样子的，F1在0.88左右，基分类器选的是lgb,rf和gbdt，其实效果不算很好，
12 | 但针对于银行信贷来说，recall是很重要的，所幸stacking后的recall是1
13 | 
14 | 我也尝试用了lgb单模型，可以看见在非平衡数据上lgb还是非常给力的。
15 | 
16 | 希望这些代码能给你提供帮助
17 | 


--------------------------------------------------------------------------------
/baseline.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 60,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import numpy as np\n",
 10 |     "import pandas as pd\n",
 11 |     "import matplotlib.pyplot as plt\n",
 12 |     "import seaborn as sns\n",
 13 |     "from collections import Counter\n",
 14 |     "from imblearn.combine import SMOTETomek   # 过采样+欠采样结合的方法处理非平衡数据集\n",
 15 |     "\n",
 16 |     "from sklearn.linear_model import LogisticRegression\n",
 17 |     "from sklearn.metrics import precision_score,recall_score\n",
 18 |     "from sklearn.model_selection import train_test_split\n",
 19 |     "from sklearn.preprocessing import StandardScaler\n",
 20 |     "from sklearn.model_selection import GridSearchCV\n",
 21 |     "from sklearn import metrics\n",
 22 |     "from sklearn.ensemble import AdaBoostClassifier as ada\n",
 23 |     "from sklearn.ensemble import GradientBoostingClassifier\n",
 24 |     "from sklearn.svm import SVC\n",
 25 |     "from sklearn.ensemble import RandomForestClassifier as RF\n",
 26 |     "from sklearn.model_selection import cross_val_score\n",
 27 |     "from sklearn.metrics import roc_auc_score\n",
 28 |     "from sklearn.ensemble import VotingClassifier\n",
 29 |     "from mlxtend.classifier import StackingClassifier\n",
 30 |     "from mlxtend.classifier import StackingCVClassifier\n",
 31 |     "\n",
 32 |     "#  Voting \n",
 33 |     "data = pd.read_csv('第一问所有特征.csv',encoding='utf-8',index_col='企业代号')\n",
 34 |     "for i in range(len(data)):\n",
 35 |     "    a='E'+str(i+1)\n",
 36 |     "    if data.loc[a,'是否违约']=='否':\n",
 37 |     "        data.loc[a,'违约']=0\n",
 38 |     "    else :\n",
 39 |     "        data.loc[a,'违约']=1\n",
 40 |     "\n",
 41 |     "x = data.iloc[:,:-4].values\n",
 42 |     "y = data.iloc[:,-1].values"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": 61,
 48 |    "metadata": {},
 49 |    "outputs": [],
 50 |    "source": [
 51 |     "x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=30)\n",
 52 |     "smote_tomek = SMOTETomek(random_state=0)\n",
 53 |     "x_train, y_train = smote_tomek.fit_resample(x_train, y_train)"
 54 |    ]
 55 |   },
 56 |   {
 57 |    "cell_type": "code",
 58 |    "execution_count": 62,
 59 |    "metadata": {},
 60 |    "outputs": [],
 61 |    "source": [
 62 |     "from lightgbm import LGBMClassifier\n",
 63 |     "\n",
 64 |     "lgb = LGBMClassifier(learning_rate=0.05,n_estimators=100,objective='binary',\n",
 65 |     "                           boosting_type='gbdt',\n",
 66 |     "                           num_leaves=2**5,\n",
 67 |     "                           max_depth=5,reg_alpha=0.5,reg_lambda=0.5,\n",
 68 |     "                           metric='auc',subsample=0.75)\n",
 69 |     "\n",
 70 |     "LR = LogisticRegression(C=0.1, class_weight=None, dual=False, fit_intercept=True,\n",
 71 |     "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
 72 |     "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
 73 |     "                   random_state=None, solver='newton-cg', tol=0.0001, verbose=0,\n",
 74 |     "                   warm_start=False)\n",
 75 |     "Ada = ada(algorithm='SAMME', base_estimator=None, learning_rate=0.1,\n",
 76 |     "                   n_estimators=100, random_state=30)\n",
 77 |     "GBDT = GradientBoostingClassifier(ccp_alpha=0.0, learning_rate=0.7,  max_depth=3)\n",
 78 |     "svc = SVC(C=0.8, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,\n",
 79 |     "    decision_function_shape='ovr', degree=3, gamma=20, kernel='rbf',\n",
 80 |     "    max_iter=-1, probability=True, random_state=None, shrinking=True, tol=0.001,\n",
 81 |     "    verbose=False)\n",
 82 |     "\n",
 83 |     "rf = RF(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
 84 |     "                       criterion='gini', max_depth=None, max_features='auto',\n",
 85 |     "                       max_leaf_nodes=None, max_samples=None,\n",
 86 |     "                       min_impurity_decrease=0.0,min_samples_leaf=1, min_samples_split=2,\n",
 87 |     "                       min_weight_fraction_leaf=0.0, n_estimators=100,\n",
 88 |     "                       n_jobs=None, oob_score=False, random_state=30, verbose=0,\n",
 89 |     "                       warm_start=False)\n",
 90 |     "\n",
 91 |     "\n",
 92 |     "sclf = StackingCVClassifier(classifiers=[Ada, GBDT, LR,rf],\n",
 93 |     "                            use_probas=True,\n",
 94 |     "                            meta_classifier=svc,\n",
 95 |     "                            random_state=30)"
 96 |    ]
 97 |   },
 98 |   {
 99 |    "cell_type": "code",
100 |    "execution_count": 63,
101 |    "metadata": {},
102 |    "outputs": [],
103 |    "source": [
104 |     "tranfer = StandardScaler()\n",
105 |     "x = tranfer.fit_transform(x)\n",
106 |     "x_train = tranfer.transform(x_train)\n",
107 |     "x_test = tranfer.transform(x_test)"
108 |    ]
109 |   },
110 |   {
111 |    "cell_type": "code",
112 |    "execution_count": 64,
113 |    "metadata": {},
114 |    "outputs": [
115 |     {
116 |      "data": {
117 |       "text/plain": [
118 |        "AdaBoostClassifier(algorithm='SAMME', learning_rate=0.1, n_estimators=100,\n",
119 |        "                   random_state=30)"
120 |       ]
121 |      },
122 |      "execution_count": 64,
123 |      "metadata": {},
124 |      "output_type": "execute_result"
125 |     }
126 |    ],
127 |    "source": [
128 |     "Ada"
129 |    ]
130 |   },
131 |   {
132 |    "cell_type": "code",
133 |    "execution_count": 65,
134 |    "metadata": {},
135 |    "outputs": [
136 |     {
137 |      "data": {
138 |       "text/html": [
139 |        "<div>\n",
140 |        "<style scoped>\n",
141 |        "    .dataframe tbody tr th:only-of-type {\n",
142 |        "        vertical-align: middle;\n",
143 |        "    }\n",
144 |        "\n",
145 |        "    .dataframe tbody tr th {\n",
146 |        "        vertical-align: top;\n",
147 |        "    }\n",
148 |        "\n",
149 |        "    .dataframe thead th {\n",
150 |        "        text-align: right;\n",
151 |        "    }\n",
152 |        "</style>\n",
153 |        "<table border=\"1\" class=\"dataframe\">\n",
154 |        "  <thead>\n",
155 |        "    <tr style=\"text-align: right;\">\n",
156 |        "      <th></th>\n",
157 |        "      <th>train_Accuracy</th>\n",
158 |        "      <th>test_Accuracy</th>\n",
159 |        "      <th>Precision</th>\n",
160 |        "      <th>Recall</th>\n",
161 |        "      <th>AUC</th>\n",
162 |        "      <th>f1</th>\n",
163 |        "    </tr>\n",
164 |        "  </thead>\n",
165 |        "  <tbody>\n",
166 |        "    <tr>\n",
167 |        "      <th>LR</th>\n",
168 |        "      <td>0.867188</td>\n",
169 |        "      <td>0.838710</td>\n",
170 |        "      <td>0.400000</td>\n",
171 |        "      <td>0.50</td>\n",
172 |        "      <td>0.759259</td>\n",
173 |        "      <td>0.444444</td>\n",
174 |        "    </tr>\n",
175 |        "    <tr>\n",
176 |        "      <th>Ada</th>\n",
177 |        "      <td>0.953125</td>\n",
178 |        "      <td>0.741935</td>\n",
179 |        "      <td>0.333333</td>\n",
180 |        "      <td>1.00</td>\n",
181 |        "      <td>0.847222</td>\n",
182 |        "      <td>0.500000</td>\n",
183 |        "    </tr>\n",
184 |        "    <tr>\n",
185 |        "      <th>GBDT</th>\n",
186 |        "      <td>1.000000</td>\n",
187 |        "      <td>0.806452</td>\n",
188 |        "      <td>0.375000</td>\n",
189 |        "      <td>0.75</td>\n",
190 |        "      <td>0.907407</td>\n",
191 |        "      <td>0.500000</td>\n",
192 |        "    </tr>\n",
193 |        "    <tr>\n",
194 |        "      <th>svc</th>\n",
195 |        "      <td>1.000000</td>\n",
196 |        "      <td>0.903226</td>\n",
197 |        "      <td>1.000000</td>\n",
198 |        "      <td>0.25</td>\n",
199 |        "      <td>0.500000</td>\n",
200 |        "      <td>0.400000</td>\n",
201 |        "    </tr>\n",
202 |        "    <tr>\n",
203 |        "      <th>rf</th>\n",
204 |        "      <td>1.000000</td>\n",
205 |        "      <td>0.838710</td>\n",
206 |        "      <td>0.444444</td>\n",
207 |        "      <td>1.00</td>\n",
208 |        "      <td>0.953704</td>\n",
209 |        "      <td>0.615385</td>\n",
210 |        "    </tr>\n",
211 |        "    <tr>\n",
212 |        "      <th>LightGBM</th>\n",
213 |        "      <td>0.984375</td>\n",
214 |        "      <td>0.774194</td>\n",
215 |        "      <td>0.333333</td>\n",
216 |        "      <td>0.75</td>\n",
217 |        "      <td>0.916667</td>\n",
218 |        "      <td>0.461538</td>\n",
219 |        "    </tr>\n",
220 |        "    <tr>\n",
221 |        "      <th>StackingClassifier</th>\n",
222 |        "      <td>0.984375</td>\n",
223 |        "      <td>0.967742</td>\n",
224 |        "      <td>0.800000</td>\n",
225 |        "      <td>1.00</td>\n",
226 |        "      <td>0.981481</td>\n",
227 |        "      <td>0.888889</td>\n",
228 |        "    </tr>\n",
229 |        "  </tbody>\n",
230 |        "</table>\n",
231 |        "</div>"
232 |       ],
233 |       "text/plain": [
234 |        "                    train_Accuracy  test_Accuracy  Precision  Recall  \\\n",
235 |        "LR                        0.867188       0.838710   0.400000    0.50   \n",
236 |        "Ada                       0.953125       0.741935   0.333333    1.00   \n",
237 |        "GBDT                      1.000000       0.806452   0.375000    0.75   \n",
238 |        "svc                       1.000000       0.903226   1.000000    0.25   \n",
239 |        "rf                        1.000000       0.838710   0.444444    1.00   \n",
240 |        "LightGBM                  0.984375       0.774194   0.333333    0.75   \n",
241 |        "StackingClassifier        0.984375       0.967742   0.800000    1.00   \n",
242 |        "\n",
243 |        "                         AUC        f1  \n",
244 |        "LR                  0.759259  0.444444  \n",
245 |        "Ada                 0.847222  0.500000  \n",
246 |        "GBDT                0.907407  0.500000  \n",
247 |        "svc                 0.500000  0.400000  \n",
248 |        "rf                  0.953704  0.615385  \n",
249 |        "LightGBM            0.916667  0.461538  \n",
250 |        "StackingClassifier  0.981481  0.888889  "
251 |       ]
252 |      },
253 |      "execution_count": 65,
254 |      "metadata": {},
255 |      "output_type": "execute_result"
256 |     }
257 |    ],
258 |    "source": [
259 |     "sclf = StackingCVClassifier(classifiers=[lgb, GBDT,rf],\n",
260 |     "                            use_probas=True,\n",
261 |     "                            meta_classifier=svc,\n",
262 |     "                            random_state=30)\n",
263 |     "\n",
264 |     "zhibiao = {}\n",
265 |     "\n",
266 |     "# weight = []\n",
267 |     "for clf, label in zip([LR, Ada, GBDT, svc, rf, lgb,sclf],\n",
268 |     "                      ['LR',\n",
269 |     "                       'Ada',\n",
270 |     "                       'GBDT',\n",
271 |     "                       'svc',\n",
272 |     "                       'rf', 'LightGBM','StackingClassifier']):\n",
273 |     "    clf.fit(x_train, y_train)\n",
274 |     "    y_predict = clf.predict(x_test)\n",
275 |     "#     print('{}在预测集模型的准确率为：\\n'.format(label), metrics.accuracy_score(y_test, y_predict))\n",
276 |     "#     print('{}在训练集模型的准确率为：\\n'.format(label), metrics.accuracy_score(y_train, clf.predict(x_train)))\n",
277 |     "#     print('{}的综合准确率为：\\n'.format(label), metrics.accuracy_score(y, clf.predict(x)))\n",
278 |     "#     print('{}的Precision为：'.format(label), precision_score(y_test, y_predict))\n",
279 |     "#     print('{}的Recall为：'.format(label), recall_score(y_test, y_predict))\n",
280 |     "    tem = metrics.roc_auc_score(y_test, y_predict)\n",
281 |     "#     weight.append(tem)\n",
282 |     "#     print('{}的ROC面积为：'.format(label), metrics.roc_auc_score(y_test, clf.predict_proba(x_test)[:,1]))\n",
283 |     "#     print('{}的f1值为：'.format(label), metrics.f1_score(y_test, y_predict))\n",
284 |     "#     print()\n",
285 |     "    \n",
286 |     "    tem_1 = [metrics.accuracy_score(y_train, clf.predict(x_train)),metrics.accuracy_score(y_test, y_predict),\n",
287 |     "            precision_score(y_test, y_predict),recall_score(y_test, y_predict),\n",
288 |     "            metrics.roc_auc_score(y_test, clf.predict_proba(x_test)[:,1]),metrics.f1_score(y_test, y_predict)]\n",
289 |     "    zhibiao[label]=tem_1\n",
290 |     "data2 = pd.DataFrame(data=zhibiao,index=['train_Accuracy','test_Accuracy',\n",
291 |     "                                'Precision','Recall','AUC','f1']).T\n",
292 |     "data2"
293 |    ]
294 |   },
295 |   {
296 |    "cell_type": "code",
297 |    "execution_count": 57,
298 |    "metadata": {},
299 |    "outputs": [
300 |     {
301 |      "data": {
302 |       "text/html": [
303 |        "<div>\n",
304 |        "<style scoped>\n",
305 |        "    .dataframe tbody tr th:only-of-type {\n",
306 |        "        vertical-align: middle;\n",
307 |        "    }\n",
308 |        "\n",
309 |        "    .dataframe tbody tr th {\n",
310 |        "        vertical-align: top;\n",
311 |        "    }\n",
312 |        "\n",
313 |        "    .dataframe thead th {\n",
314 |        "        text-align: right;\n",
315 |        "    }\n",
316 |        "</style>\n",
317 |        "<table border=\"1\" class=\"dataframe\">\n",
318 |        "  <thead>\n",
319 |        "    <tr style=\"text-align: right;\">\n",
320 |        "      <th></th>\n",
321 |        "      <th>train_Accuracy</th>\n",
322 |        "      <th>test_Accuracy</th>\n",
323 |        "      <th>Precision</th>\n",
324 |        "      <th>Recall</th>\n",
325 |        "      <th>AUC</th>\n",
326 |        "      <th>f1</th>\n",
327 |        "    </tr>\n",
328 |        "  </thead>\n",
329 |        "  <tbody>\n",
330 |        "    <tr>\n",
331 |        "      <th>LightGBM</th>\n",
332 |        "      <td>0.956522</td>\n",
333 |        "      <td>0.967742</td>\n",
334 |        "      <td>0.8</td>\n",
335 |        "      <td>1.0</td>\n",
336 |        "      <td>0.805556</td>\n",
337 |        "      <td>0.888889</td>\n",
338 |        "    </tr>\n",
339 |        "  </tbody>\n",
340 |        "</table>\n",
341 |        "</div>"
342 |       ],
343 |       "text/plain": [
344 |        "          train_Accuracy  test_Accuracy  Precision  Recall       AUC        f1\n",
345 |        "LightGBM        0.956522       0.967742        0.8     1.0  0.805556  0.888889"
346 |       ]
347 |      },
348 |      "execution_count": 57,
349 |      "metadata": {},
350 |      "output_type": "execute_result"
351 |     }
352 |    ],
353 |    "source": [
354 |     "# LGB单模(对非平衡数据集设置is_unbalance)\n",
355 |     "x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=30)\n",
356 |     "clf = LGBMClassifier(learning_rate=0.05,n_estimators=100,objective='binary',\n",
357 |     "                           boosting_type='gbdt',\n",
358 |     "                           num_leaves=2**5,\n",
359 |     "                           max_depth=5,reg_alpha=0.5,reg_lambda=0.5,is_unbalance=True,\n",
360 |     "                           metric='auc',subsample=0.75)\n",
361 |     "clf.fit(x_train,y_train)\n",
362 |     "pd.DataFrame(data=[metrics.accuracy_score(y_train, clf.predict(x_train)),metrics.accuracy_score(y_test, y_predict),\n",
363 |     "            precision_score(y_test, y_predict),recall_score(y_test, y_predict),\n",
364 |     "            metrics.roc_auc_score(y_test, clf.predict_proba(x_test)[:,1]),metrics.f1_score(y_test, y_predict)],index=['train_Accuracy','test_Accuracy',\n",
365 |     "                                'Precision','Recall','AUC','f1'],columns=['LightGBM']).T"
366 |    ]
367 |   }
368 |  ],
369 |  "metadata": {
370 |   "interpreter": {
371 |    "hash": "07efdcd4b820c98a756949507a4d29d7862823915ec7477944641bea022f4f62"
372 |   },
373 |   "kernelspec": {
374 |    "display_name": "Python 3.8.8 ('base')",
375 |    "language": "python",
376 |    "name": "python3"
377 |   },
378 |   "language_info": {
379 |    "codemirror_mode": {
380 |     "name": "ipython",
381 |     "version": 3
382 |    },
383 |    "file_extension": ".py",
384 |    "mimetype": "text/x-python",
385 |    "name": "python",
386 |    "nbconvert_exporter": "python",
387 |    "pygments_lexer": "ipython3",
388 |    "version": "3.8.8"
389 |   },
390 |   "orig_nbformat": 4
391 |  },
392 |  "nbformat": 4,
393 |  "nbformat_minor": 2
394 | }
395 | 


--------------------------------------------------------------------------------
/第一问信用评级的描述性统计.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 3,
 16 |    "metadata": {},
 17 |    "outputs": [
 18 |     {
 19 |      "data": {
 20 |       "text/html": [
 21 |        "<div>\n",
 22 |        "<style scoped>\n",
 23 |        "    .dataframe tbody tr th:only-of-type {\n",
 24 |        "        vertical-align: middle;\n",
 25 |        "    }\n",
 26 |        "\n",
 27 |        "    .dataframe tbody tr th {\n",
 28 |        "        vertical-align: top;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe thead th {\n",
 32 |        "        text-align: right;\n",
 33 |        "    }\n",
 34 |        "</style>\n",
 35 |        "<table border=\"1\" class=\"dataframe\">\n",
 36 |        "  <thead>\n",
 37 |        "    <tr style=\"text-align: right;\">\n",
 38 |        "      <th></th>\n",
 39 |        "      <th>违约概率</th>\n",
 40 |        "      <th>信誉评级</th>\n",
 41 |        "    </tr>\n",
 42 |        "  </thead>\n",
 43 |        "  <tbody>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>0</th>\n",
 46 |        "      <td>0.144146</td>\n",
 47 |        "      <td>A</td>\n",
 48 |        "    </tr>\n",
 49 |        "    <tr>\n",
 50 |        "      <th>1</th>\n",
 51 |        "      <td>0.109683</td>\n",
 52 |        "      <td>A</td>\n",
 53 |        "    </tr>\n",
 54 |        "    <tr>\n",
 55 |        "      <th>2</th>\n",
 56 |        "      <td>0.087636</td>\n",
 57 |        "      <td>C</td>\n",
 58 |        "    </tr>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>3</th>\n",
 61 |        "      <td>0.100442</td>\n",
 62 |        "      <td>C</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>4</th>\n",
 66 |        "      <td>0.132734</td>\n",
 67 |        "      <td>B</td>\n",
 68 |        "    </tr>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>...</th>\n",
 71 |        "      <td>...</td>\n",
 72 |        "      <td>...</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>118</th>\n",
 76 |        "      <td>0.690629</td>\n",
 77 |        "      <td>D</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>119</th>\n",
 81 |        "      <td>0.863239</td>\n",
 82 |        "      <td>D</td>\n",
 83 |        "    </tr>\n",
 84 |        "    <tr>\n",
 85 |        "      <th>120</th>\n",
 86 |        "      <td>0.669896</td>\n",
 87 |        "      <td>D</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>121</th>\n",
 91 |        "      <td>0.813119</td>\n",
 92 |        "      <td>D</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>122</th>\n",
 96 |        "      <td>0.858223</td>\n",
 97 |        "      <td>D</td>\n",
 98 |        "    </tr>\n",
 99 |        "  </tbody>\n",
100 |        "</table>\n",
101 |        "<p>123 rows × 2 columns</p>\n",
102 |        "</div>"
103 |       ],
104 |       "text/plain": [
105 |        "         违约概率 信誉评级\n",
106 |        "0    0.144146    A\n",
107 |        "1    0.109683    A\n",
108 |        "2    0.087636    C\n",
109 |        "3    0.100442    C\n",
110 |        "4    0.132734    B\n",
111 |        "..        ...  ...\n",
112 |        "118  0.690629    D\n",
113 |        "119  0.863239    D\n",
114 |        "120  0.669896    D\n",
115 |        "121  0.813119    D\n",
116 |        "122  0.858223    D\n",
117 |        "\n",
118 |        "[123 rows x 2 columns]"
119 |       ]
120 |      },
121 |      "execution_count": 3,
122 |      "metadata": {},
123 |      "output_type": "execute_result"
124 |     }
125 |    ],
126 |    "source": [
127 |     "data = pd.read_csv('违约风险.csv',encoding='gbk')\n",
128 |     "data"
129 |    ]
130 |   },
131 |   {
132 |    "cell_type": "code",
133 |    "execution_count": 17,
134 |    "metadata": {},
135 |    "outputs": [],
136 |    "source": [
137 |     "A_max = data[data['信誉评级']=='A']['违约概率'].max()\n",
138 |     "A_min = data[data['信誉评级']=='A']['违约概率'].min()\n",
139 |     "\n",
140 |     "B_max = data[data['信誉评级']=='B']['违约概率'].max()\n",
141 |     "B_min = data[data['信誉评级']=='B']['违约概率'].min()\n",
142 |     "\n",
143 |     "C_max = data[data['信誉评级']=='C']['违约概率'].max()\n",
144 |     "C_min = data[data['信誉评级']=='C']['违约概率'].min()\n",
145 |     "\n",
146 |     "D_max = data[data['信誉评级']=='D']['违约概率'].max()\n",
147 |     "D_min = data[data['信誉评级']=='D']['违约概率'].min()"
148 |    ]
149 |   },
150 |   {
151 |    "cell_type": "code",
152 |    "execution_count": 18,
153 |    "metadata": {},
154 |    "outputs": [
155 |     {
156 |      "data": {
157 |       "text/html": [
158 |        "<div>\n",
159 |        "<style scoped>\n",
160 |        "    .dataframe tbody tr th:only-of-type {\n",
161 |        "        vertical-align: middle;\n",
162 |        "    }\n",
163 |        "\n",
164 |        "    .dataframe tbody tr th {\n",
165 |        "        vertical-align: top;\n",
166 |        "    }\n",
167 |        "\n",
168 |        "    .dataframe thead th {\n",
169 |        "        text-align: right;\n",
170 |        "    }\n",
171 |        "</style>\n",
172 |        "<table border=\"1\" class=\"dataframe\">\n",
173 |        "  <thead>\n",
174 |        "    <tr style=\"text-align: right;\">\n",
175 |        "      <th></th>\n",
176 |        "      <th>A</th>\n",
177 |        "      <th>B</th>\n",
178 |        "      <th>C</th>\n",
179 |        "      <th>D</th>\n",
180 |        "    </tr>\n",
181 |        "  </thead>\n",
182 |        "  <tbody>\n",
183 |        "    <tr>\n",
184 |        "      <th>Max</th>\n",
185 |        "      <td>0.434712</td>\n",
186 |        "      <td>0.756349</td>\n",
187 |        "      <td>0.638270</td>\n",
188 |        "      <td>0.882178</td>\n",
189 |        "    </tr>\n",
190 |        "    <tr>\n",
191 |        "      <th>Min</th>\n",
192 |        "      <td>0.078757</td>\n",
193 |        "      <td>0.100952</td>\n",
194 |        "      <td>0.087636</td>\n",
195 |        "      <td>0.237270</td>\n",
196 |        "    </tr>\n",
197 |        "  </tbody>\n",
198 |        "</table>\n",
199 |        "</div>"
200 |       ],
201 |       "text/plain": [
202 |        "            A         B         C         D\n",
203 |        "Max  0.434712  0.756349  0.638270  0.882178\n",
204 |        "Min  0.078757  0.100952  0.087636  0.237270"
205 |       ]
206 |      },
207 |      "execution_count": 18,
208 |      "metadata": {},
209 |      "output_type": "execute_result"
210 |     }
211 |    ],
212 |    "source": [
213 |     "dd = {'A':[A_max,A_min],\n",
214 |     "     'B':[B_max,B_min],\n",
215 |     "     'C':[C_max,C_min],\n",
216 |     "     'D':[D_max,D_min]}\n",
217 |     "\n",
218 |     "d1 = pd.DataFrame(data=dd,index=['Max','Min'])\n",
219 |     "d1"
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "code",
224 |    "execution_count": 27,
225 |    "metadata": {},
226 |    "outputs": [
227 |     {
228 |      "data": {
229 |       "text/html": [
230 |        "<div>\n",
231 |        "<style scoped>\n",
232 |        "    .dataframe tbody tr th:only-of-type {\n",
233 |        "        vertical-align: middle;\n",
234 |        "    }\n",
235 |        "\n",
236 |        "    .dataframe tbody tr th {\n",
237 |        "        vertical-align: top;\n",
238 |        "    }\n",
239 |        "\n",
240 |        "    .dataframe thead th {\n",
241 |        "        text-align: right;\n",
242 |        "    }\n",
243 |        "</style>\n",
244 |        "<table border=\"1\" class=\"dataframe\">\n",
245 |        "  <thead>\n",
246 |        "    <tr style=\"text-align: right;\">\n",
247 |        "      <th></th>\n",
248 |        "      <th>A</th>\n",
249 |        "      <th>B</th>\n",
250 |        "      <th>C</th>\n",
251 |        "      <th>D</th>\n",
252 |        "    </tr>\n",
253 |        "  </thead>\n",
254 |        "  <tbody>\n",
255 |        "    <tr>\n",
256 |        "      <th>count</th>\n",
257 |        "      <td>27.000000</td>\n",
258 |        "      <td>38.000000</td>\n",
259 |        "      <td>34.000000</td>\n",
260 |        "      <td>24.000000</td>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>mean</th>\n",
264 |        "      <td>0.145062</td>\n",
265 |        "      <td>0.181696</td>\n",
266 |        "      <td>0.208571</td>\n",
267 |        "      <td>0.709669</td>\n",
268 |        "    </tr>\n",
269 |        "    <tr>\n",
270 |        "      <th>std</th>\n",
271 |        "      <td>0.067785</td>\n",
272 |        "      <td>0.107809</td>\n",
273 |        "      <td>0.146612</td>\n",
274 |        "      <td>0.169678</td>\n",
275 |        "    </tr>\n",
276 |        "    <tr>\n",
277 |        "      <th>min</th>\n",
278 |        "      <td>0.078757</td>\n",
279 |        "      <td>0.100952</td>\n",
280 |        "      <td>0.087636</td>\n",
281 |        "      <td>0.237270</td>\n",
282 |        "    </tr>\n",
283 |        "    <tr>\n",
284 |        "      <th>25%</th>\n",
285 |        "      <td>0.110293</td>\n",
286 |        "      <td>0.137316</td>\n",
287 |        "      <td>0.121182</td>\n",
288 |        "      <td>0.651753</td>\n",
289 |        "    </tr>\n",
290 |        "    <tr>\n",
291 |        "      <th>50%</th>\n",
292 |        "      <td>0.128696</td>\n",
293 |        "      <td>0.161150</td>\n",
294 |        "      <td>0.156689</td>\n",
295 |        "      <td>0.780061</td>\n",
296 |        "    </tr>\n",
297 |        "    <tr>\n",
298 |        "      <th>75%</th>\n",
299 |        "      <td>0.162311</td>\n",
300 |        "      <td>0.191359</td>\n",
301 |        "      <td>0.198689</td>\n",
302 |        "      <td>0.814742</td>\n",
303 |        "    </tr>\n",
304 |        "    <tr>\n",
305 |        "      <th>max</th>\n",
306 |        "      <td>0.434712</td>\n",
307 |        "      <td>0.756349</td>\n",
308 |        "      <td>0.638270</td>\n",
309 |        "      <td>0.882178</td>\n",
310 |        "    </tr>\n",
311 |        "  </tbody>\n",
312 |        "</table>\n",
313 |        "</div>"
314 |       ],
315 |       "text/plain": [
316 |        "               A          B          C          D\n",
317 |        "count  27.000000  38.000000  34.000000  24.000000\n",
318 |        "mean    0.145062   0.181696   0.208571   0.709669\n",
319 |        "std     0.067785   0.107809   0.146612   0.169678\n",
320 |        "min     0.078757   0.100952   0.087636   0.237270\n",
321 |        "25%     0.110293   0.137316   0.121182   0.651753\n",
322 |        "50%     0.128696   0.161150   0.156689   0.780061\n",
323 |        "75%     0.162311   0.191359   0.198689   0.814742\n",
324 |        "max     0.434712   0.756349   0.638270   0.882178"
325 |       ]
326 |      },
327 |      "execution_count": 27,
328 |      "metadata": {},
329 |      "output_type": "execute_result"
330 |     }
331 |    ],
332 |    "source": [
333 |     "A_des = data[data['信誉评级']=='A']['违约概率'].describe()\n",
334 |     "B_des = data[data['信誉评级']=='B']['违约概率'].describe()\n",
335 |     "C_des = data[data['信誉评级']=='C']['违约概率'].describe()\n",
336 |     "D_des = data[data['信誉评级']=='D']['违约概率'].describe()\n",
337 |     "\n",
338 |     "dd2 = {'A':A_des,'B':B_des,'C':C_des,'D':D_des}\n",
339 |     "d2 = pd.DataFrame(data=dd2)\n",
340 |     "d2"
341 |    ]
342 |   },
343 |   {
344 |    "cell_type": "code",
345 |    "execution_count": 29,
346 |    "metadata": {},
347 |    "outputs": [],
348 |    "source": [
349 |     "d2.to_csv('各类信誉评级的违约风险的描述性统计分析.csv',encoding='gbk')"
350 |    ]
351 |   },
352 |   {
353 |    "cell_type": "code",
354 |    "execution_count": null,
355 |    "metadata": {},
356 |    "outputs": [],
357 |    "source": []
358 |   },
359 |   {
360 |    "cell_type": "code",
361 |    "execution_count": null,
362 |    "metadata": {},
363 |    "outputs": [],
364 |    "source": []
365 |   },
366 |   {
367 |    "cell_type": "code",
368 |    "execution_count": null,
369 |    "metadata": {},
370 |    "outputs": [],
371 |    "source": []
372 |   }
373 |  ],
374 |  "metadata": {
375 |   "kernelspec": {
376 |    "display_name": "Python [conda env:root] *",
377 |    "language": "python",
378 |    "name": "conda-root-py"
379 |   },
380 |   "language_info": {
381 |    "codemirror_mode": {
382 |     "name": "ipython",
383 |     "version": 3
384 |    },
385 |    "file_extension": ".py",
386 |    "mimetype": "text/x-python",
387 |    "name": "python",
388 |    "nbconvert_exporter": "python",
389 |    "pygments_lexer": "ipython3",
390 |    "version": "3.7.6"
391 |   },
392 |   "toc": {
393 |    "base_numbering": 1,
394 |    "nav_menu": {},
395 |    "number_sections": true,
396 |    "sideBar": true,
397 |    "skip_h1_title": false,
398 |    "title_cell": "Table of Contents",
399 |    "title_sidebar": "Contents",
400 |    "toc_cell": false,
401 |    "toc_position": {},
402 |    "toc_section_display": true,
403 |    "toc_window_display": false
404 |   }
405 |  },
406 |  "nbformat": 4,
407 |  "nbformat_minor": 4
408 | }
409 | 


--------------------------------------------------------------------------------
/第一问所有特征.csv:
--------------------------------------------------------------------------------
  1 | 企业代号,销-进金额,增值税,销1,销2,销3,销4,进1,进2,进3,进4,进项发票的作废比例,销项发票的作废比例,绝对数变化,比例变化,是否扭亏为盈利,是否变为亏损,下属部门,分公司 ,公司,个体经营,评级,信誉评级,是否违约
  2 | E1,-1898184082,0,179,51,51,71,332,74,27,3,0.055797733,0.027620222,-193872136,1.720613861,0,0,0,0,1,0,1,A,否
  3 | E2,426297552.3,28261615.82,1147,268,121,43,2424,780,314,103,0.022421943,0.082002046,110302536.5,2.197674176,0,0,0,0,1,0,1,A,否
  4 | E3,514987171,88562269.38,48,48,25,14,386,103,58,23,0.042534532,0.015993021,-115477286.1,0.516353348,0,0,0,1,0,0,3,C,否
  5 | E4,1511803093,254330043.4,16,10,0,0,94,21,13,2,0.066308244,0.085163604,-1168509293,0.053642121,0,0,0,0,1,0,3,C,否
  6 | E5,691527.38,548958.88,16,15,2,0,324,47,19,2,0.039188566,0.051886792,4068217.15,85.22708692,0,0,0,0,1,0,2,B,否
  7 | E6,45673584.07,9086998.62,85,38,18,1,1170,235,96,13,0.046132134,0.132129278,14520912.32,6.220033757,0,0,0,0,1,0,1,A,否
  8 | E7,450248079.4,79329020.55,1004,101,103,3,1043,392,126,10,0.034664427,0.01435759,-170352223.8,0.282999939,0,0,0,1,0,0,1,A,否
  9 | E8,186366411.1,13359969.4,2051,428,169,31,1758,547,216,72,0.033679446,0.113103448,10175963.7,1.190343495,0,0,0,0,1,0,1,A,否
 10 | E9,294700968.1,48008699.68,26,28,24,45,497,138,72,26,0.02189611,0.024720623,8701373.76,1.102641628,0,0,0,1,0,0,1,A,否
 11 | E10,334674157.2,10308763.71,14,2,7,3,707,122,51,0,0.057847205,0.091549296,82858784.61,5.695238829,0,0,0,0,1,0,2,B,否
 12 | E11,5011729.91,2085745.11,1,1,2,0,353,96,13,3,0.042665726,0.05908684,-38346246.26,0.062246969,0,0,0,0,1,0,3,C,否
 13 | E12,119554241,12226064.87,1,3,1,0,298,77,16,2,0.021714922,0.077192982,-84557485.89,0.314231061,0,0,0,0,1,0,2,B,否
 14 | E13,114691249.5,19162604.52,2699,342,111,25,456,150,73,43,0.015888336,0.149531543,17290905.08,1.624659042,0,0,0,0,1,0,1,A,否
 15 | E14,86038310.36,17351210.64,499,176,145,0,609,170,126,0,0.077716547,0.071642686,8017782.6,1.260860968,0,0,0,0,0,1,3,C,否
 16 | E15,207585880.2,7211027.52,0,0,1,1,27,5,1,0,0,0.063018242,28666792.4,2.030952353,0,0,0,0,1,0,1,A,否
 17 | E16,209132769.2,4130668.31,34,9,8,2,63,11,3,0,0.003448276,0.111617312,39872630.5,4.427526479,0,0,0,0,1,0,1,A,否
 18 | E17,12371632.79,0,136,37,6,3,633,165,67,4,0.056157505,0.170118343,10825143.39,4.609111121,0,0,0,0,1,0,1,A,否
 19 | E18,50065149.39,0,32,5,8,1,507,94,38,2,0.053772767,0.094488189,17393819.63,25.37000438,0,0,0,0,1,0,1,A,否
 20 | E19,-10663999.95,0,359,105,32,12,112,35,15,5,0.026246719,0.089706357,457386.04,1.295208096,0,0,0,0,1,0,1,A,否
 21 | E20,-2938233.73,871931.22,20,1,3,1,51,10,8,1,0.078761062,0.051480051,4408596.54,3.448482477,0,0,0,0,1,0,2,B,否
 22 | E21,-11541727.45,2010367.05,312,13,0,0,398,67,13,2,0.071799308,0.025920873,9020452.64,-107.8554226,1,0,0,0,1,0,2,B,否
 23 | E22,39408223.26,1007767.46,29,12,3,1,54,17,8,1,0.055900621,0.125480154,34495523.8,-68.36411556,1,0,0,0,1,0,1,A,否
 24 | E23,7810606.37,1343556.27,58,27,10,23,463,150,56,13,0.03009493,0.022969188,-6130097.84,-3.152684243,0,1,0,0,1,0,2,B,否
 25 | E24,63461390.07,2581218.68,25,17,4,2,272,73,18,4,0.021006351,0.080808081,21065382.97,3.750814974,0,0,0,0,1,0,1,A,否
 26 | E25,28738558.94,4790430.02,182,37,13,1,267,76,20,4,0.013475177,0.167689162,3950781.03,1.871990389,0,0,0,0,1,0,3,C,否
 27 | E26,-1938217.2,0,29,12,1,0,80,23,9,5,0.041719343,0.107142857,801968.45,-1.535171354,1,0,0,0,1,0,1,A,否
 28 | E27,-2964169.13,0,118,36,13,10,307,66,21,9,0.035087719,0.053814714,340587.89,-4.576462138,1,0,0,0,1,0,1,A,否
 29 | E28,47653987.22,4585203.06,1,1,2,1,46,14,1,0,0.076923077,0.077328647,19643668.89,7.404078616,0,0,0,0,1,0,2,B,否
 30 | E29,45010590.57,1778869.77,1,1,1,0,15,1,1,0,0.04,0.012631579,11138949.26,1.85630192,0,0,0,0,1,0,3,C,是
 31 | E30,49372586.08,3403861.37,3,3,1,0,145,17,7,0,0.018567639,0.06625,2738199.31,1.234802735,0,0,0,0,1,0,2,B,否
 32 | E31,42826768.62,6338508.75,64,28,37,22,87,10,5,5,0.019417476,0.041027607,7131326.48,1.679119834,0,0,0,0,1,0,1,A,否
 33 | E32,41734977.49,1132413.07,9,0,1,0,207,49,16,0,0.005307856,0.152173913,11818843.08,2.063600841,0,0,0,0,1,0,2,B,否
 34 | E33,-13685226.15,3473876.56,61,16,7,0,186,42,9,3,0.123743233,0.150046598,-1247606.58,0.512545099,0,0,0,0,1,0,2,B,否
 35 | E34,30811458.94,1004529,56,6,2,0,379,56,12,0,0.103074924,0.157001414,-1442409.79,140.7276366,0,0,0,0,1,0,2,B,否
 36 | E35,1307511.65,0,20,5,4,2,57,29,13,2,0.053811659,0.042857143,4954392.81,-11.28383944,1,0,0,0,1,0,2,B,否
 37 | E36,14510309.69,1949388.05,87,60,51,0,319,62,36,0,0.045232274,0.076276665,5859723.15,3.214112585,0,0,0,0,1,0,4,D,是
 38 | E37,-1828933.02,0,219,44,12,1,55,16,7,1,0.042071197,0.06991359,20100.51,0.945329365,0,0,0,0,1,0,2,B,否
 39 | E38,33531866.64,617679.99,5,2,1,0,191,40,5,0,0.033299697,0.121019108,3241096.45,1.331340181,0,0,0,0,1,0,2,B,否
 40 | E39,28820097.95,3723255.27,1,0,1,0,44,9,1,0,0.010638298,0.106060606,13935775.47,7.45272558,0,0,0,0,1,0,3,C,否
 41 | E40,29114217.69,546512.99,452,31,0,0,641,111,29,13,0.025412961,0.093997735,13206723.03,6.115626836,0,0,0,0,1,0,3,C,否
 42 | E41,26983203.31,460999.03,5,3,3,2,369,86,23,8,0.031972455,0.087481146,12254350.03,4.989140651,0,0,0,0,1,0,3,C,否
 43 | E42,26225027.98,0,23,5,0,0,6,1,0,0,0,0.100917431,12910420.96,12.13534949,0,0,0,0,1,0,1,A,否
 44 | E43,14107614.55,711302.84,3,2,0,0,15,4,0,0,0.128205128,0.126530612,1390239.32,1.182075685,0,0,0,0,1,0,2,B,否
 45 | E44,2524250.34,326537.44,13,12,3,2,137,52,20,2,0.020833333,0.07926078,899638.66,6.562504224,0,0,0,0,1,0,3,C,否
 46 | E45,459652.75,301217.76,55,8,0,0,92,19,3,0,0.013333333,0.061538462,-697757.92,-5.818097757,0,1,0,0,0,1,2,B,是
 47 | E46,6666931.75,305058.31,104,27,8,1,342,69,21,3,0.020440252,0.087268994,1283506.09,12.06990003,0,0,0,0,1,0,3,C,否
 48 | E47,5743256.84,1001210.12,414,161,106,79,234,66,46,28,0.032358003,0.046048891,1285307.17,2.966145392,0,0,0,0,1,0,3,C,否
 49 | E48,37027025.99,5451628.06,35,13,5,6,164,43,21,3,0.020242915,0.05511811,17195806.14,5.250937641,0,0,0,0,1,0,1,A,否
 50 | E49,9628430.92,956642.35,244,4,0,0,551,130,28,4,0.026832642,0.101364522,-4707428.38,0.389280788,0,0,0,0,1,0,3,C,否
 51 | E50,16419820.69,709422.73,4,1,0,0,54,11,1,0,0.055837563,0.105263158,6781297.75,2.710812996,0,0,0,0,1,0,3,C,否
 52 | E51,7169019.19,532024.51,87,22,15,5,45,8,6,2,0.004415011,0.068156425,5553169.22,149.5400353,0,0,0,0,1,0,2,B,否
 53 | E52,1785006.11,266081.32,8,2,1,0,108,20,3,0,0.037647059,0.245382586,1095999.81,2.928640925,0,0,0,0,1,0,4,D,是
 54 | E53,1234243.06,0,33,6,4,0,48,13,1,0,0.049206349,0.127753304,244683.34,1.233460399,0,0,0,0,1,0,3,C,否
 55 | E54,24868467.73,3137410.18,700,187,212,11,347,76,28,6,0.054136253,0.081690945,3650147.27,1.559499811,0,0,0,0,1,0,1,A,否
 56 | E55,11859438.55,1377481.76,18,2,2,0,96,32,6,3,0.086269745,0.249152542,-3163800.21,0.461382188,0,0,0,1,0,0,3,C,否
 57 | E56,-1408942.97,0,21,6,6,4,114,34,9,5,0.040799334,0.074747475,590087.43,0.608077187,0,0,0,0,1,0,3,C,否
 58 | E57,2973362.72,671931.59,18,6,1,0,32,8,1,0,0.061538462,0.118721461,-2307020.6,-520.3782614,0,1,0,0,1,0,2,B,否
 59 | E58,14939854.55,1044924.28,18,2,2,0,284,52,18,0,0.028846154,0.268041237,4623582.12,2.631909484,0,0,0,0,1,0,2,B,否
 60 | E59,7399026.38,1165767.6,131,34,15,5,52,17,5,2,0.030965392,0.038157282,2076239.55,2.668089467,0,0,0,0,1,0,1,A,否
 61 | E60,3153536.31,0,3,4,1,0,102,24,2,0,0.014869888,0.173489279,2762867.14,16.64818925,0,0,0,0,1,0,2,B,否
 62 | E61,16040129.65,1704753.35,47,8,9,1,28,8,6,2,0.014150943,0.018574297,-1426691.21,0.75169374,0,0,0,0,1,0,2,B,否
 63 | E62,8262640.47,497880.69,20,4,2,1,108,27,12,1,0.005660377,0.127853881,-1325522.5,0.640706858,0,0,0,1,0,0,2,B,否
 64 | E63,10859983.19,3946576.94,29,11,2,0,237,34,19,2,0.029879212,0.071322437,-7595933.39,0.163752575,0,0,0,0,1,0,2,B,否
 65 | E64,8798256.56,55237.46,131,20,10,1,17,2,2,0,0,0.066909091,412503.15,1.153526918,0,0,0,0,1,0,1,A,否
 66 | E65,2726684.71,237765.7,36,14,4,4,21,12,5,0,0.01362862,0.06185567,745267.07,3.181304821,0,0,0,0,1,0,2,B,否
 67 | E66,-375084.44,0,113,25,12,1,19,5,4,2,0.003466205,0.075110457,1573358.29,163.8030821,0,0,0,0,1,0,2,B,否
 68 | E67,4315445.45,99554,18,3,2,0,157,25,12,1,0.030911901,0.106976744,2189387.65,5.055198896,0,0,0,0,1,0,2,B,否
 69 | E68,5866711.11,89627.09,5,2,0,0,1,1,0,0,0,0.109589041,-2731449.09,0.364643359,0,0,0,0,1,0,3,C,否
 70 | E69,3636062.74,109081.89,12,4,2,0,1,0,0,0,0,0.109028961,2661870.58,9.974805767,0,0,1,0,0,0,3,C,否
 71 | E70,3595798.73,580622.56,39,8,5,3,138,29,13,7,0.022963368,0.188581315,-2036647.49,0.059261052,0,0,0,0,1,0,2,B,否
 72 | E71,417041.18,0,260,18,4,0,214,48,19,0,0.042891183,0.042666667,5842485.55,-0.270946377,1,0,0,0,1,0,2,B,否
 73 | E72,2943665.95,0,25,3,0,0,41,9,3,0,0.025641026,0.290322581,1453197.42,-13.39267755,1,0,0,0,1,0,3,C,否
 74 | E73,5350093.41,909143.31,48,7,2,1,84,21,8,5,0.00990099,0.055084746,-1344863.84,0.494727487,0,0,0,0,1,0,3,C,否
 75 | E74,3649790.04,0,8,6,3,2,7,1,0,0,0,0.077477477,1388223.66,6.797415479,0,0,0,0,1,0,2,B,否
 76 | E75,3859608.51,26412.04,7451,9,2,1,34,12,4,3,0.025362319,0.068284229,-1700637.8,0.219843181,0,0,0,0,1,0,3,C,否
 77 | E76,3156443.92,203043.27,58,4,9,2,78,16,7,1,0.011428571,0.089795918,940249.39,2.752940948,0,0,0,0,1,0,2,B,否
 78 | E77,3607798.82,159249.17,0,1,1,0,13,2,0,1,0.018518519,0.023255814,-759119.19,0.402139273,0,0,0,0,1,0,3,C,否
 79 | E78,6029427.49,260670.99,30,5,2,0,11,4,1,0,0,0.074626866,-2691870.88,0.187109816,0,0,0,0,0,1,3,C,否
 80 | E79,363491.02,0,9,4,1,1,30,11,3,2,0.012987013,0.139534884,1034964.7,-1.507861627,1,0,0,0,1,0,2,B,否
 81 | E80,1148651.19,27552.75,38,0,0,0,82,15,6,0,0.012658228,0.020833333,3297244.36,-5.026949012,1,0,0,0,1,0,3,C,否
 82 | E81,1330514.4,221435.23,70,30,17,2,49,13,5,1,0.028436019,0.061633282,182894.31,1.580709088,0,0,0,0,1,0,1,A,否
 83 | E82,1385376.45,238891.41,7,0,1,0,41,17,10,0,0.012698413,0.023323615,118211.17,1.384650542,0,0,0,0,1,0,4,D,是
 84 | E83,-34876613.63,0,130,30,0,0,162,52,37,8,0.066089965,0.080736544,-11859813.95,3.545184778,0,0,0,0,1,0,2,B,否
 85 | E84,3392431.19,521610.51,24,7,4,0,16,1,1,1,0.018518519,0.106425703,641060.92,1.908647944,0,0,0,0,1,0,1,A,否
 86 | E85,2247393.78,55871.8,14,6,1,2,25,6,6,1,0.004366812,0.156996587,509292.93,3.370016672,0,0,0,0,1,0,2,B,否
 87 | E86,411411.22,54856.36,3,4,0,0,29,6,1,0,0.007246377,0.136363636,-606338.28,0.224465111,0,0,0,1,0,0,3,C,否
 88 | E87,2288881.09,240920.4,5,4,3,1,62,17,2,1,0.021108179,0.040540541,674008.58,3.983327704,0,0,0,0,1,0,3,C,是
 89 | E88,1877583.81,160137.38,78,8,0,0,17,7,1,1,0,0.09,181422.33,1.393914056,0,0,0,0,1,0,1,A,否
 90 | E89,-824452.26,159405.57,16,4,4,0,6,5,1,0,0.030769231,0.040697674,2630392.22,-0.244160693,1,0,0,0,1,0,1,A,否
 91 | E90,2488785.48,167307.28,38,8,3,0,29,6,0,0,0.028776978,0.283524904,426767.62,1.71430123,0,0,0,0,1,0,3,C,否
 92 | E91,930397.99,148985.33,65,7,1,0,20,8,6,1,0.050847458,0.046511628,267744.88,2.254806928,0,0,0,0,1,0,1,A,否
 93 | E92,2060494.4,55579.19,11,2,0,0,73,12,4,0,0.004694836,0.076923077,1226750.25,4.818772443,0,0,0,0,1,0,3,C,否
 94 | E93,1158753.81,26196.36,19,5,4,0,53,8,4,0,0.023474178,0.047297297,190487.11,1.773236926,0,0,0,0,1,0,2,B,否
 95 | E94,1039150.21,29299.68,54,2,0,0,4,0,0,0,0,0.091836735,296547.2,2.761899454,0,0,0,0,1,0,3,C,否
 96 | E95,2309683.68,69258.77,446,32,7,0,0,0,1,0,0,0.053669222,-173150.47,0.762139235,0,0,0,0,1,0,2,B,否
 97 | E96,-880797.48,0,3,0,0,0,4,2,0,0,0,0.1,1348697.76,33.85250329,0,0,0,0,1,0,3,C,否
 98 | E97,952646.12,28016.78,44,17,2,0,1,0,1,0,0,0.034090909,428086.28,2.842571436,0,0,1,0,0,0,2,B,否
 99 | E98,1203728.22,31893.6,20,3,2,0,25,1,1,0,0.019607843,0.130718954,-106852.63,0.805678733,0,0,0,0,1,0,2,B,否
100 | E99,-5203665.22,0,1,1,0,0,73,7,1,0,0.010227273,0.375,-1114717.37,-1.215629991,0,1,0,0,1,0,4,D,是
101 | E100,650279.93,17886.26,9,2,1,1,15,5,1,0,0,0.01010101,-111912.9,0.641697941,0,0,0,0,1,0,4,D,是
102 | E101,294643.81,44576.19,2,0,0,0,4,2,0,0,0,0.492063492,-119859.57,0.421671447,0,0,0,0,1,0,4,D,是
103 | E102,-2841555.25,0,91,7,2,0,28,21,12,9,0.02739726,0.146892655,43268.35,0.951715913,0,0,0,0,1,0,4,D,是
104 | E103,990178.47,62712.09,16,3,0,0,56,7,2,0,0.01744186,0.15625,49319.54,1.085415704,0,0,0,0,1,0,4,D,是
105 | E104,262386.36,7863.64,10,0,0,0,1,0,0,0,0,0.095238095,103233.01,2.299433945,0,0,0,0,1,0,3,C,否
106 | E105,917382.45,26701.44,101,0,0,0,2,2,0,0,0,0.008196721,-134853.56,0.572421947,0,0,1,0,0,0,3,C,否
107 | E106,526975.73,15241.03,95,6,2,0,15,4,0,0,0.027777778,0.098039216,139940.23,2.157468663,0,0,0,0,1,0,2,B,否
108 | E107,682155.01,40934.99,2,0,1,0,5,2,0,0,0,0.37037037,600297.72,10.30893452,0,0,0,0,1,0,4,D,是
109 | E108,92174.11,0,18,1,0,0,51,18,1,0,0,0,-123849.11,0.035964429,0,0,0,0,1,0,4,D,是
110 | E109,439509.33,13926.67,16,1,0,0,5,2,0,0,0,0.303030303,274393.5,7.229384822,0,0,0,0,1,0,4,D,是
111 | E110,195956.47,5831.04,29,5,0,0,0,0,1,0,0,0.253012048,21642.65,1.78831463,0,0,1,0,0,0,3,C,否
112 | E111,124997.02,100848.16,5,0,1,3,74,15,4,2,0.050359712,0.184,-271144.93,-2.37302917,0,1,0,0,1,0,4,D,是
113 | E112,86946.74,19202.37,1,1,0,0,17,6,2,0,0.037735849,0.272727273,208206.57,2.69992051,0,0,0,0,1,0,4,D,是
114 | E113,-1006740.82,0,2,1,0,0,26,8,1,0,0.019230769,0.340425532,-82420.22,-0.038912999,0,1,0,0,1,0,4,D,是
115 | E114,-397912.31,0,19,1,3,0,15,4,1,0,0.092105263,0.12,-356779.9,-5.032003203,0,1,0,0,1,0,4,D,是
116 | E115,55005.68,1634.32,3,0,0,0,2,0,0,0,0,0.333333333,35728.16,4.706717462,0,0,0,0,1,0,4,D,是
117 | E116,228821.67,6742.4,24,1,0,0,8,0,0,0,0,0.085106383,-75814.26,0.066151003,0,0,0,0,1,0,4,D,是
118 | E117,516642.52,1405.48,0,1,0,0,3,0,0,0,0,0.409090909,211072.46,2.381499614,0,0,0,0,1,0,4,D,是
119 | E118,120774.03,0,111,5,0,0,7,2,0,0,0.068965517,0.055555556,-141118.15,-0.339462906,0,1,0,0,1,0,4,D,是
120 | E119,-184120.28,0,12,1,1,0,7,6,2,2,0.003174603,0.142857143,-68619.22,6.999116995,0,0,0,0,1,0,4,D,是
121 | E120,162416.14,3780.94,6,0,0,0,13,3,0,0,0.027777778,0.689655172,8830.95,1.139033405,0,0,0,0,1,0,4,D,是
122 | E121,-972024.16,0,110,6,0,0,7,2,2,0,0,0.123655914,690652.18,-0.075121715,1,0,0,0,1,0,4,D,是
123 | E122,7342.16,0,67,2,0,0,18,3,1,0,0.020833333,0.13559322,-27347.29,-0.681495628,0,1,0,0,1,0,4,D,是
124 | E123,199443.4,27276.3,3,1,1,0,1,1,0,0,0,0.492307692,17453.84,1.824360564,0,0,0,0,1,0,4,D,是
125 | 


--------------------------------------------------------------------------------
/第一问：作废发票计算.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 146,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "import pandas as pd\n",
  10 |     "import numpy as np\n",
  11 |     "import matplotlib.pyplot as plt\n",
  12 |     "from datetime import datetime\n",
  13 |     "import time"
  14 |    ]
  15 |   },
  16 |   {
  17 |    "cell_type": "markdown",
  18 |    "metadata": {},
  19 |    "source": [
  20 |     "# 进销口分析"
  21 |    ]
  22 |   },
  23 |   {
  24 |    "cell_type": "code",
  25 |    "execution_count": 2,
  26 |    "metadata": {},
  27 |    "outputs": [],
  28 |    "source": [
  29 |     "input1 = pd.read_excel('附件1.xlsx',sheet_name='进项发票信息')\n",
  30 |     "output1 = pd.read_excel('附件1.xlsx',sheet_name='销项发票信息')"
  31 |    ]
  32 |   },
  33 |   {
  34 |    "cell_type": "code",
  35 |    "execution_count": 22,
  36 |    "metadata": {},
  37 |    "outputs": [],
  38 |    "source": [
  39 |     "for num in range(1,124):\n",
  40 |     "    id1 = 'E'+str(num)\n",
  41 |     "    input1[input1['企业代号']==id1]"
  42 |    ]
  43 |   },
  44 |   {
  45 |    "cell_type": "code",
  46 |    "execution_count": 41,
  47 |    "metadata": {},
  48 |    "outputs": [
  49 |     {
  50 |      "data": {
  51 |       "text/plain": [
  52 |        "0.05579773321708806"
  53 |       ]
  54 |      },
  55 |      "execution_count": 41,
  56 |      "metadata": {},
  57 |      "output_type": "execute_result"
  58 |     }
  59 |    ],
  60 |    "source": [
  61 |     "num = 1\n",
  62 |     "id1 = 'E'+str(num)\n",
  63 |     "tem = input1[input1['企业代号']==id1]\n",
  64 |     "all_num = tem.shape[0]\n",
  65 |     "fei_num = tem[tem['发票状态']=='作废发票'].shape[0]\n",
  66 |     "ratio = fei_num/all_num\n",
  67 |     "ratio"
  68 |    ]
  69 |   },
  70 |   {
  71 |    "cell_type": "code",
  72 |    "execution_count": 47,
  73 |    "metadata": {},
  74 |    "outputs": [],
  75 |    "source": [
  76 |     "r_in=[]\n",
  77 |     "\n",
  78 |     "for num in range(1,124):\n",
  79 |     "    id1 = 'E'+str(num)\n",
  80 |     "    tem = input1[input1['企业代号']==id1]\n",
  81 |     "    all_num = tem.shape[0]\n",
  82 |     "    fei_num = tem[tem['发票状态']=='作废发票'].shape[0]\n",
  83 |     "    ratio = fei_num/all_num\n",
  84 |     "    \n",
  85 |     "    r_in.append(ratio)\n",
  86 |     "    \n",
  87 |     "r_out=[]\n",
  88 |     "\n",
  89 |     "for num in range(1,124):\n",
  90 |     "    id1 = 'E'+str(num)\n",
  91 |     "    tem = output1[output1['企业代号']==id1]\n",
  92 |     "    all_num = tem.shape[0]\n",
  93 |     "    fei_num = tem[tem['发票状态']=='作废发票'].shape[0]\n",
  94 |     "    ratio = fei_num/all_num\n",
  95 |     "    \n",
  96 |     "    r_out.append(ratio)\n",
  97 |     "\n",
  98 |     "    \n",
  99 |     "\n",
 100 |     "name=[]    \n",
 101 |     "for num in range(1,124):\n",
 102 |     "    id1 = 'E'+str(num)\n",
 103 |     "    name.append(id1)\n",
 104 |     "    "
 105 |    ]
 106 |   },
 107 |   {
 108 |    "cell_type": "code",
 109 |    "execution_count": 55,
 110 |    "metadata": {},
 111 |    "outputs": [],
 112 |    "source": [
 113 |     "in_num=[]\n",
 114 |     "for num in range(1,124):\n",
 115 |     "    id1 = 'E'+str(num)\n",
 116 |     "    tem = input1[input1['企业代号']==id1]\n",
 117 |     "    all_num = tem.shape[0]\n",
 118 |     "    \n",
 119 |     "    in_num.append(all_num)\n",
 120 |     "    \n",
 121 |     "out_num=[]\n",
 122 |     "for num in range(1,124):\n",
 123 |     "    id1 = 'E'+str(num)\n",
 124 |     "    tem = output1[output1['企业代号']==id1]\n",
 125 |     "    all_num = tem.shape[0]\n",
 126 |     "    \n",
 127 |     "    out_num.append(all_num)"
 128 |    ]
 129 |   },
 130 |   {
 131 |    "cell_type": "code",
 132 |    "execution_count": 56,
 133 |    "metadata": {},
 134 |    "outputs": [
 135 |     {
 136 |      "data": {
 137 |       "text/html": [
 138 |        "<div>\n",
 139 |        "<style scoped>\n",
 140 |        "    .dataframe tbody tr th:only-of-type {\n",
 141 |        "        vertical-align: middle;\n",
 142 |        "    }\n",
 143 |        "\n",
 144 |        "    .dataframe tbody tr th {\n",
 145 |        "        vertical-align: top;\n",
 146 |        "    }\n",
 147 |        "\n",
 148 |        "    .dataframe thead th {\n",
 149 |        "        text-align: right;\n",
 150 |        "    }\n",
 151 |        "</style>\n",
 152 |        "<table border=\"1\" class=\"dataframe\">\n",
 153 |        "  <thead>\n",
 154 |        "    <tr style=\"text-align: right;\">\n",
 155 |        "      <th></th>\n",
 156 |        "      <th>企业名称</th>\n",
 157 |        "      <th>进项发票的作废比例</th>\n",
 158 |        "      <th>销项发票的作废比例</th>\n",
 159 |        "      <th>进项发票数</th>\n",
 160 |        "      <th>销项发票数</th>\n",
 161 |        "    </tr>\n",
 162 |        "  </thead>\n",
 163 |        "  <tbody>\n",
 164 |        "    <tr>\n",
 165 |        "      <th>0</th>\n",
 166 |        "      <td>E1</td>\n",
 167 |        "      <td>0.055798</td>\n",
 168 |        "      <td>0.027620</td>\n",
 169 |        "      <td>3441</td>\n",
 170 |        "      <td>8110</td>\n",
 171 |        "    </tr>\n",
 172 |        "    <tr>\n",
 173 |        "      <th>1</th>\n",
 174 |        "      <td>E2</td>\n",
 175 |        "      <td>0.022422</td>\n",
 176 |        "      <td>0.082002</td>\n",
 177 |        "      <td>32156</td>\n",
 178 |        "      <td>12707</td>\n",
 179 |        "    </tr>\n",
 180 |        "    <tr>\n",
 181 |        "      <th>2</th>\n",
 182 |        "      <td>E3</td>\n",
 183 |        "      <td>0.042535</td>\n",
 184 |        "      <td>0.015993</td>\n",
 185 |        "      <td>4561</td>\n",
 186 |        "      <td>24073</td>\n",
 187 |        "    </tr>\n",
 188 |        "    <tr>\n",
 189 |        "      <th>3</th>\n",
 190 |        "      <td>E4</td>\n",
 191 |        "      <td>0.066308</td>\n",
 192 |        "      <td>0.085164</td>\n",
 193 |        "      <td>558</td>\n",
 194 |        "      <td>2231</td>\n",
 195 |        "    </tr>\n",
 196 |        "    <tr>\n",
 197 |        "      <th>4</th>\n",
 198 |        "      <td>E5</td>\n",
 199 |        "      <td>0.039189</td>\n",
 200 |        "      <td>0.051887</td>\n",
 201 |        "      <td>2169</td>\n",
 202 |        "      <td>1060</td>\n",
 203 |        "    </tr>\n",
 204 |        "    <tr>\n",
 205 |        "      <th>...</th>\n",
 206 |        "      <td>...</td>\n",
 207 |        "      <td>...</td>\n",
 208 |        "      <td>...</td>\n",
 209 |        "      <td>...</td>\n",
 210 |        "      <td>...</td>\n",
 211 |        "    </tr>\n",
 212 |        "    <tr>\n",
 213 |        "      <th>118</th>\n",
 214 |        "      <td>E119</td>\n",
 215 |        "      <td>0.003175</td>\n",
 216 |        "      <td>0.142857</td>\n",
 217 |        "      <td>315</td>\n",
 218 |        "      <td>21</td>\n",
 219 |        "    </tr>\n",
 220 |        "    <tr>\n",
 221 |        "      <th>119</th>\n",
 222 |        "      <td>E120</td>\n",
 223 |        "      <td>0.027778</td>\n",
 224 |        "      <td>0.689655</td>\n",
 225 |        "      <td>36</td>\n",
 226 |        "      <td>29</td>\n",
 227 |        "    </tr>\n",
 228 |        "    <tr>\n",
 229 |        "      <th>120</th>\n",
 230 |        "      <td>E121</td>\n",
 231 |        "      <td>0.000000</td>\n",
 232 |        "      <td>0.123656</td>\n",
 233 |        "      <td>50</td>\n",
 234 |        "      <td>186</td>\n",
 235 |        "    </tr>\n",
 236 |        "    <tr>\n",
 237 |        "      <th>121</th>\n",
 238 |        "      <td>E122</td>\n",
 239 |        "      <td>0.020833</td>\n",
 240 |        "      <td>0.135593</td>\n",
 241 |        "      <td>48</td>\n",
 242 |        "      <td>118</td>\n",
 243 |        "    </tr>\n",
 244 |        "    <tr>\n",
 245 |        "      <th>122</th>\n",
 246 |        "      <td>E123</td>\n",
 247 |        "      <td>0.000000</td>\n",
 248 |        "      <td>0.492308</td>\n",
 249 |        "      <td>3</td>\n",
 250 |        "      <td>65</td>\n",
 251 |        "    </tr>\n",
 252 |        "  </tbody>\n",
 253 |        "</table>\n",
 254 |        "<p>123 rows × 5 columns</p>\n",
 255 |        "</div>"
 256 |       ],
 257 |       "text/plain": [
 258 |        "     企业名称  进项发票的作废比例  销项发票的作废比例  进项发票数  销项发票数\n",
 259 |        "0      E1   0.055798   0.027620   3441   8110\n",
 260 |        "1      E2   0.022422   0.082002  32156  12707\n",
 261 |        "2      E3   0.042535   0.015993   4561  24073\n",
 262 |        "3      E4   0.066308   0.085164    558   2231\n",
 263 |        "4      E5   0.039189   0.051887   2169   1060\n",
 264 |        "..    ...        ...        ...    ...    ...\n",
 265 |        "118  E119   0.003175   0.142857    315     21\n",
 266 |        "119  E120   0.027778   0.689655     36     29\n",
 267 |        "120  E121   0.000000   0.123656     50    186\n",
 268 |        "121  E122   0.020833   0.135593     48    118\n",
 269 |        "122  E123   0.000000   0.492308      3     65\n",
 270 |        "\n",
 271 |        "[123 rows x 5 columns]"
 272 |       ]
 273 |      },
 274 |      "execution_count": 56,
 275 |      "metadata": {},
 276 |      "output_type": "execute_result"
 277 |     }
 278 |    ],
 279 |    "source": [
 280 |     "data = {'企业名称':name,\n",
 281 |     "    '进项发票的作废比例':r_in   ,\n",
 282 |     "      '销项发票的作废比例':r_out  ,\n",
 283 |     "        '进项发票数':in_num ,\n",
 284 |     "        '销项发票数':out_num\n",
 285 |     "}\n",
 286 |     "\n",
 287 |     "df=pd.DataFrame(data=data)\n",
 288 |     "df"
 289 |    ]
 290 |   },
 291 |   {
 292 |    "cell_type": "code",
 293 |    "execution_count": 57,
 294 |    "metadata": {},
 295 |    "outputs": [],
 296 |    "source": [
 297 |     "df.to_csv('附件1作废发票比例.csv',encoding='gbk')"
 298 |    ]
 299 |   },
 300 |   {
 301 |    "cell_type": "markdown",
 302 |    "metadata": {},
 303 |    "source": [
 304 |     "# 企业文字提取"
 305 |    ]
 306 |   },
 307 |   {
 308 |    "cell_type": "code",
 309 |    "execution_count": 59,
 310 |    "metadata": {},
 311 |    "outputs": [
 312 |     {
 313 |      "data": {
 314 |       "text/html": [
 315 |        "<div>\n",
 316 |        "<style scoped>\n",
 317 |        "    .dataframe tbody tr th:only-of-type {\n",
 318 |        "        vertical-align: middle;\n",
 319 |        "    }\n",
 320 |        "\n",
 321 |        "    .dataframe tbody tr th {\n",
 322 |        "        vertical-align: top;\n",
 323 |        "    }\n",
 324 |        "\n",
 325 |        "    .dataframe thead th {\n",
 326 |        "        text-align: right;\n",
 327 |        "    }\n",
 328 |        "</style>\n",
 329 |        "<table border=\"1\" class=\"dataframe\">\n",
 330 |        "  <thead>\n",
 331 |        "    <tr style=\"text-align: right;\">\n",
 332 |        "      <th></th>\n",
 333 |        "      <th>企业代号</th>\n",
 334 |        "      <th>企业名称</th>\n",
 335 |        "      <th>信誉评级</th>\n",
 336 |        "      <th>是否违约</th>\n",
 337 |        "    </tr>\n",
 338 |        "  </thead>\n",
 339 |        "  <tbody>\n",
 340 |        "    <tr>\n",
 341 |        "      <th>0</th>\n",
 342 |        "      <td>E1</td>\n",
 343 |        "      <td>***电器销售有限公司</td>\n",
 344 |        "      <td>A</td>\n",
 345 |        "      <td>否</td>\n",
 346 |        "    </tr>\n",
 347 |        "    <tr>\n",
 348 |        "      <th>1</th>\n",
 349 |        "      <td>E2</td>\n",
 350 |        "      <td>***技术有限责任公司</td>\n",
 351 |        "      <td>A</td>\n",
 352 |        "      <td>否</td>\n",
 353 |        "    </tr>\n",
 354 |        "    <tr>\n",
 355 |        "      <th>2</th>\n",
 356 |        "      <td>E3</td>\n",
 357 |        "      <td>***电子(中国)有限公司***分公司</td>\n",
 358 |        "      <td>C</td>\n",
 359 |        "      <td>否</td>\n",
 360 |        "    </tr>\n",
 361 |        "    <tr>\n",
 362 |        "      <th>3</th>\n",
 363 |        "      <td>E4</td>\n",
 364 |        "      <td>***发展有限责任公司</td>\n",
 365 |        "      <td>C</td>\n",
 366 |        "      <td>否</td>\n",
 367 |        "    </tr>\n",
 368 |        "    <tr>\n",
 369 |        "      <th>4</th>\n",
 370 |        "      <td>E5</td>\n",
 371 |        "      <td>***供应链管理有限公司</td>\n",
 372 |        "      <td>B</td>\n",
 373 |        "      <td>否</td>\n",
 374 |        "    </tr>\n",
 375 |        "    <tr>\n",
 376 |        "      <th>...</th>\n",
 377 |        "      <td>...</td>\n",
 378 |        "      <td>...</td>\n",
 379 |        "      <td>...</td>\n",
 380 |        "      <td>...</td>\n",
 381 |        "    </tr>\n",
 382 |        "    <tr>\n",
 383 |        "      <th>118</th>\n",
 384 |        "      <td>E119</td>\n",
 385 |        "      <td>***药房</td>\n",
 386 |        "      <td>D</td>\n",
 387 |        "      <td>是</td>\n",
 388 |        "    </tr>\n",
 389 |        "    <tr>\n",
 390 |        "      <th>119</th>\n",
 391 |        "      <td>E120</td>\n",
 392 |        "      <td>***陈列广告有限公司</td>\n",
 393 |        "      <td>D</td>\n",
 394 |        "      <td>是</td>\n",
 395 |        "    </tr>\n",
 396 |        "    <tr>\n",
 397 |        "      <th>120</th>\n",
 398 |        "      <td>E121</td>\n",
 399 |        "      <td>***药业连锁有限公司***药店</td>\n",
 400 |        "      <td>D</td>\n",
 401 |        "      <td>是</td>\n",
 402 |        "    </tr>\n",
 403 |        "    <tr>\n",
 404 |        "      <th>121</th>\n",
 405 |        "      <td>E122</td>\n",
 406 |        "      <td>***商贸有限责任公司</td>\n",
 407 |        "      <td>D</td>\n",
 408 |        "      <td>是</td>\n",
 409 |        "    </tr>\n",
 410 |        "    <tr>\n",
 411 |        "      <th>122</th>\n",
 412 |        "      <td>E123</td>\n",
 413 |        "      <td>***创科技有限责任公司</td>\n",
 414 |        "      <td>D</td>\n",
 415 |        "      <td>是</td>\n",
 416 |        "    </tr>\n",
 417 |        "  </tbody>\n",
 418 |        "</table>\n",
 419 |        "<p>123 rows × 4 columns</p>\n",
 420 |        "</div>"
 421 |       ],
 422 |       "text/plain": [
 423 |        "     企业代号                 企业名称 信誉评级 是否违约\n",
 424 |        "0      E1          ***电器销售有限公司    A    否\n",
 425 |        "1      E2          ***技术有限责任公司    A    否\n",
 426 |        "2      E3  ***电子(中国)有限公司***分公司    C    否\n",
 427 |        "3      E4          ***发展有限责任公司    C    否\n",
 428 |        "4      E5         ***供应链管理有限公司    B    否\n",
 429 |        "..    ...                  ...  ...  ...\n",
 430 |        "118  E119                ***药房    D    是\n",
 431 |        "119  E120          ***陈列广告有限公司    D    是\n",
 432 |        "120  E121     ***药业连锁有限公司***药店    D    是\n",
 433 |        "121  E122          ***商贸有限责任公司    D    是\n",
 434 |        "122  E123         ***创科技有限责任公司    D    是\n",
 435 |        "\n",
 436 |        "[123 rows x 4 columns]"
 437 |       ]
 438 |      },
 439 |      "execution_count": 59,
 440 |      "metadata": {},
 441 |      "output_type": "execute_result"
 442 |     }
 443 |    ],
 444 |    "source": [
 445 |     "data = pd.read_excel('附件1.xlsx',sheet_name='企业信息')\n",
 446 |     "data"
 447 |    ]
 448 |   },
 449 |   {
 450 |    "cell_type": "code",
 451 |    "execution_count": null,
 452 |    "metadata": {},
 453 |    "outputs": [],
 454 |    "source": []
 455 |   },
 456 |   {
 457 |    "cell_type": "code",
 458 |    "execution_count": null,
 459 |    "metadata": {},
 460 |    "outputs": [],
 461 |    "source": []
 462 |   },
 463 |   {
 464 |    "cell_type": "code",
 465 |    "execution_count": null,
 466 |    "metadata": {},
 467 |    "outputs": [],
 468 |    "source": []
 469 |   },
 470 |   {
 471 |    "cell_type": "markdown",
 472 |    "metadata": {},
 473 |    "source": [
 474 |     "# 时间序列分析"
 475 |    ]
 476 |   },
 477 |   {
 478 |    "cell_type": "code",
 479 |    "execution_count": 67,
 480 |    "metadata": {},
 481 |    "outputs": [],
 482 |    "source": [
 483 |     "for i in range(len(input1)):         # 删除作废发票\n",
 484 |     "    if input1.loc[i,'发票状态']=='作废发票':\n",
 485 |     "        input1.drop(i,inplace=True)"
 486 |    ]
 487 |   },
 488 |   {
 489 |    "cell_type": "code",
 490 |    "execution_count": 68,
 491 |    "metadata": {},
 492 |    "outputs": [],
 493 |    "source": [
 494 |     "for i in range(len(output1)):\n",
 495 |     "    if output1.loc[i,'发票状态']=='作废发票':\n",
 496 |     "        output1.drop(i,inplace=True)"
 497 |    ]
 498 |   },
 499 |   {
 500 |    "cell_type": "code",
 501 |    "execution_count": 72,
 502 |    "metadata": {},
 503 |    "outputs": [],
 504 |    "source": [
 505 |     "input1.reset_index(drop = True,inplace=True)\n",
 506 |     "output1.reset_index(drop = True,inplace=True)"
 507 |    ]
 508 |   },
 509 |   {
 510 |    "cell_type": "code",
 511 |    "execution_count": 73,
 512 |    "metadata": {},
 513 |    "outputs": [],
 514 |    "source": [
 515 |     "input1['开票日期'] = pd.to_datetime(input1['开票日期'])\n",
 516 |     "output1['开票日期'] = pd.to_datetime(output1['开票日期'])"
 517 |    ]
 518 |   },
 519 |   {
 520 |    "cell_type": "code",
 521 |    "execution_count": 219,
 522 |    "metadata": {},
 523 |    "outputs": [],
 524 |    "source": [
 525 |     "deal1=[]\n",
 526 |     "deal2=[]\n",
 527 |     "deal3=[]\n",
 528 |     "deal4=[]\n",
 529 |     "deal5=[]\n",
 530 |     "for num in range(1,124):      # 遍历目标企业\n",
 531 |     "    l_1 = 0\n",
 532 |     "    l_2 = 0\n",
 533 |     "    l_3 = 0       # 一年、两年、三年、四年的交易方\n",
 534 |     "    l_4 = 0\n",
 535 |     "    l_5 = 0\n",
 536 |     "\n",
 537 |     "    id1 = 'E'+str(num)\n",
 538 |     "    a = input1[input1['企业代号']==id1]\n",
 539 |     "    a = a.reset_index(drop=True)\n",
 540 |     "    other = np.unique(a['销方单位代号'])    # 交易方代号的唯一值\n",
 541 |     "    \n",
 542 |     "    year = a['开票日期'][len(a)-1].year - a['开票日期'][0].year+1  \n",
 543 |     "    begin = a['开票日期'][0].year\n",
 544 |     "    \n",
 545 |     "    for i in range(len(other)):       # 遍历交易企业\n",
 546 |     "        cou=0\n",
 547 |     "        company = other[i]      # 选中的交易企业\n",
 548 |     "        for j in range(year):    # 遍历每一年\n",
 549 |     "            tem = a[(a['开票日期'] >str(begin+j) )& (a['开票日期'] <str(begin+j+1))]['销方单位代号'].unique()  # 一年内的交易企业\n",
 550 |     "            if company in tem:\n",
 551 |     "                cou +=1\n",
 552 |     "                \n",
 553 |     "        if cou == 1:\n",
 554 |     "            l_1+=1\n",
 555 |     "        elif cou == 2:\n",
 556 |     "            l_2+=1\n",
 557 |     "        elif cou ==3:\n",
 558 |     "            l_3+= 1\n",
 559 |     "        elif cou==4:\n",
 560 |     "            l_4+=1\n",
 561 |     "        elif cou == 5:\n",
 562 |     "            l_5+=1\n",
 563 |     "                \n",
 564 |     "                \n",
 565 |     "    deal1.append(l_1)\n",
 566 |     "    deal2.append(l_2)\n",
 567 |     "    deal3.append(l_3)        \n",
 568 |     "    deal4.append(l_4)        \n",
 569 |     "    deal5.append(l_5)"
 570 |    ]
 571 |   },
 572 |   {
 573 |    "cell_type": "code",
 574 |    "execution_count": 222,
 575 |    "metadata": {},
 576 |    "outputs": [],
 577 |    "source": [
 578 |     "da1 = {'持续一年期的交易企业个数':deal1,\n",
 579 |     "     '持续二年期的交易企业个数': deal2,\n",
 580 |     "     '持续三年期的交易企业个数': deal3,\n",
 581 |     "     '持续四年前的交易企业个数':deal4,\n",
 582 |     "       '持续五年期的交易企业个数':deal5\n",
 583 |     "     }"
 584 |    ]
 585 |   },
 586 |   {
 587 |    "cell_type": "code",
 588 |    "execution_count": 223,
 589 |    "metadata": {},
 590 |    "outputs": [
 591 |     {
 592 |      "data": {
 593 |       "text/html": [
 594 |        "<div>\n",
 595 |        "<style scoped>\n",
 596 |        "    .dataframe tbody tr th:only-of-type {\n",
 597 |        "        vertical-align: middle;\n",
 598 |        "    }\n",
 599 |        "\n",
 600 |        "    .dataframe tbody tr th {\n",
 601 |        "        vertical-align: top;\n",
 602 |        "    }\n",
 603 |        "\n",
 604 |        "    .dataframe thead th {\n",
 605 |        "        text-align: right;\n",
 606 |        "    }\n",
 607 |        "</style>\n",
 608 |        "<table border=\"1\" class=\"dataframe\">\n",
 609 |        "  <thead>\n",
 610 |        "    <tr style=\"text-align: right;\">\n",
 611 |        "      <th></th>\n",
 612 |        "      <th>持续一年期的交易企业个数</th>\n",
 613 |        "      <th>持续二年期的交易企业个数</th>\n",
 614 |        "      <th>持续三年期的交易企业个数</th>\n",
 615 |        "      <th>持续四年前的交易企业个数</th>\n",
 616 |        "      <th>持续五年期的交易企业个数</th>\n",
 617 |        "    </tr>\n",
 618 |        "  </thead>\n",
 619 |        "  <tbody>\n",
 620 |        "    <tr>\n",
 621 |        "      <th>0</th>\n",
 622 |        "      <td>332</td>\n",
 623 |        "      <td>74</td>\n",
 624 |        "      <td>27</td>\n",
 625 |        "      <td>3</td>\n",
 626 |        "      <td>0</td>\n",
 627 |        "    </tr>\n",
 628 |        "    <tr>\n",
 629 |        "      <th>1</th>\n",
 630 |        "      <td>2424</td>\n",
 631 |        "      <td>780</td>\n",
 632 |        "      <td>314</td>\n",
 633 |        "      <td>103</td>\n",
 634 |        "      <td>0</td>\n",
 635 |        "    </tr>\n",
 636 |        "    <tr>\n",
 637 |        "      <th>2</th>\n",
 638 |        "      <td>386</td>\n",
 639 |        "      <td>103</td>\n",
 640 |        "      <td>58</td>\n",
 641 |        "      <td>23</td>\n",
 642 |        "      <td>0</td>\n",
 643 |        "    </tr>\n",
 644 |        "    <tr>\n",
 645 |        "      <th>3</th>\n",
 646 |        "      <td>94</td>\n",
 647 |        "      <td>21</td>\n",
 648 |        "      <td>13</td>\n",
 649 |        "      <td>2</td>\n",
 650 |        "      <td>0</td>\n",
 651 |        "    </tr>\n",
 652 |        "    <tr>\n",
 653 |        "      <th>4</th>\n",
 654 |        "      <td>324</td>\n",
 655 |        "      <td>47</td>\n",
 656 |        "      <td>19</td>\n",
 657 |        "      <td>2</td>\n",
 658 |        "      <td>0</td>\n",
 659 |        "    </tr>\n",
 660 |        "    <tr>\n",
 661 |        "      <th>...</th>\n",
 662 |        "      <td>...</td>\n",
 663 |        "      <td>...</td>\n",
 664 |        "      <td>...</td>\n",
 665 |        "      <td>...</td>\n",
 666 |        "      <td>...</td>\n",
 667 |        "    </tr>\n",
 668 |        "    <tr>\n",
 669 |        "      <th>118</th>\n",
 670 |        "      <td>7</td>\n",
 671 |        "      <td>6</td>\n",
 672 |        "      <td>2</td>\n",
 673 |        "      <td>2</td>\n",
 674 |        "      <td>0</td>\n",
 675 |        "    </tr>\n",
 676 |        "    <tr>\n",
 677 |        "      <th>119</th>\n",
 678 |        "      <td>13</td>\n",
 679 |        "      <td>3</td>\n",
 680 |        "      <td>0</td>\n",
 681 |        "      <td>0</td>\n",
 682 |        "      <td>0</td>\n",
 683 |        "    </tr>\n",
 684 |        "    <tr>\n",
 685 |        "      <th>120</th>\n",
 686 |        "      <td>7</td>\n",
 687 |        "      <td>2</td>\n",
 688 |        "      <td>2</td>\n",
 689 |        "      <td>0</td>\n",
 690 |        "      <td>0</td>\n",
 691 |        "    </tr>\n",
 692 |        "    <tr>\n",
 693 |        "      <th>121</th>\n",
 694 |        "      <td>18</td>\n",
 695 |        "      <td>3</td>\n",
 696 |        "      <td>1</td>\n",
 697 |        "      <td>0</td>\n",
 698 |        "      <td>0</td>\n",
 699 |        "    </tr>\n",
 700 |        "    <tr>\n",
 701 |        "      <th>122</th>\n",
 702 |        "      <td>1</td>\n",
 703 |        "      <td>1</td>\n",
 704 |        "      <td>0</td>\n",
 705 |        "      <td>0</td>\n",
 706 |        "      <td>0</td>\n",
 707 |        "    </tr>\n",
 708 |        "  </tbody>\n",
 709 |        "</table>\n",
 710 |        "<p>123 rows × 5 columns</p>\n",
 711 |        "</div>"
 712 |       ],
 713 |       "text/plain": [
 714 |        "     持续一年期的交易企业个数  持续二年期的交易企业个数  持续三年期的交易企业个数  持续四年前的交易企业个数  持续五年期的交易企业个数\n",
 715 |        "0             332            74            27             3             0\n",
 716 |        "1            2424           780           314           103             0\n",
 717 |        "2             386           103            58            23             0\n",
 718 |        "3              94            21            13             2             0\n",
 719 |        "4             324            47            19             2             0\n",
 720 |        "..            ...           ...           ...           ...           ...\n",
 721 |        "118             7             6             2             2             0\n",
 722 |        "119            13             3             0             0             0\n",
 723 |        "120             7             2             2             0             0\n",
 724 |        "121            18             3             1             0             0\n",
 725 |        "122             1             1             0             0             0\n",
 726 |        "\n",
 727 |        "[123 rows x 5 columns]"
 728 |       ]
 729 |      },
 730 |      "execution_count": 223,
 731 |      "metadata": {},
 732 |      "output_type": "execute_result"
 733 |     }
 734 |    ],
 735 |    "source": [
 736 |     "jx = pd.DataFrame(data=da1)\n",
 737 |     "jx"
 738 |    ]
 739 |   },
 740 |   {
 741 |    "cell_type": "code",
 742 |    "execution_count": 301,
 743 |    "metadata": {},
 744 |    "outputs": [],
 745 |    "source": [
 746 |     "jx.to_csv('上游持续交易企业数.csv',encoding='gbk')"
 747 |    ]
 748 |   },
 749 |   {
 750 |    "cell_type": "code",
 751 |    "execution_count": 230,
 752 |    "metadata": {},
 753 |    "outputs": [],
 754 |    "source": [
 755 |     "deal1=[]\n",
 756 |     "deal2=[]\n",
 757 |     "deal3=[]\n",
 758 |     "deal4=[]\n",
 759 |     "for num in range(1,124):      # 遍历目标企业\n",
 760 |     "    l_1 = 0\n",
 761 |     "    l_2 = 0\n",
 762 |     "    l_3 = 0       # 一年、两年、三年、四年的交易方\n",
 763 |     "    l_4 = 0\n",
 764 |     "\n",
 765 |     "    id1 = 'E'+str(num)\n",
 766 |     "    a = output1[output1['企业代号']==id1]\n",
 767 |     "    a = a.reset_index(drop=True)\n",
 768 |     "    other = np.unique(a['购方单位代号'])    # 交易方代号的唯一值\n",
 769 |     "    \n",
 770 |     "    year = a['开票日期'][len(a)-1].year - a['开票日期'][0].year+1  \n",
 771 |     "    begin = a['开票日期'][0].year\n",
 772 |     "    \n",
 773 |     "    for i in range(len(other)):       # 遍历交易企业\n",
 774 |     "        cou=0\n",
 775 |     "        company = other[i]      # 选中的交易企业\n",
 776 |     "        for j in range(year):    # 遍历每一年\n",
 777 |     "            tem = a[(a['开票日期'] >str(begin+j) )& (a['开票日期'] <str(begin+j+1))]['购方单位代号'].unique()  # 一年内的交易企业\n",
 778 |     "            if company in tem:\n",
 779 |     "                cou +=1\n",
 780 |     "                \n",
 781 |     "        if cou == 1:\n",
 782 |     "            l_1+=1\n",
 783 |     "        elif cou == 2:\n",
 784 |     "            l_2+=1\n",
 785 |     "        elif cou ==3:\n",
 786 |     "            l_3+= 1\n",
 787 |     "        elif cou==4:\n",
 788 |     "            l_4+=1\n",
 789 |     "\n",
 790 |     "                \n",
 791 |     "                \n",
 792 |     "    deal1.append(l_1)\n",
 793 |     "    deal2.append(l_2)\n",
 794 |     "    deal3.append(l_3)        \n",
 795 |     "    deal4.append(l_4)        \n"
 796 |    ]
 797 |   },
 798 |   {
 799 |    "cell_type": "code",
 800 |    "execution_count": 231,
 801 |    "metadata": {},
 802 |    "outputs": [
 803 |     {
 804 |      "data": {
 805 |       "text/html": [
 806 |        "<div>\n",
 807 |        "<style scoped>\n",
 808 |        "    .dataframe tbody tr th:only-of-type {\n",
 809 |        "        vertical-align: middle;\n",
 810 |        "    }\n",
 811 |        "\n",
 812 |        "    .dataframe tbody tr th {\n",
 813 |        "        vertical-align: top;\n",
 814 |        "    }\n",
 815 |        "\n",
 816 |        "    .dataframe thead th {\n",
 817 |        "        text-align: right;\n",
 818 |        "    }\n",
 819 |        "</style>\n",
 820 |        "<table border=\"1\" class=\"dataframe\">\n",
 821 |        "  <thead>\n",
 822 |        "    <tr style=\"text-align: right;\">\n",
 823 |        "      <th></th>\n",
 824 |        "      <th>持续一年期的交易企业个数</th>\n",
 825 |        "      <th>持续二年期的交易企业个数</th>\n",
 826 |        "      <th>持续三年期的交易企业个数</th>\n",
 827 |        "      <th>持续四年前的交易企业个数</th>\n",
 828 |        "    </tr>\n",
 829 |        "  </thead>\n",
 830 |        "  <tbody>\n",
 831 |        "    <tr>\n",
 832 |        "      <th>0</th>\n",
 833 |        "      <td>179</td>\n",
 834 |        "      <td>51</td>\n",
 835 |        "      <td>51</td>\n",
 836 |        "      <td>71</td>\n",
 837 |        "    </tr>\n",
 838 |        "    <tr>\n",
 839 |        "      <th>1</th>\n",
 840 |        "      <td>1147</td>\n",
 841 |        "      <td>268</td>\n",
 842 |        "      <td>121</td>\n",
 843 |        "      <td>43</td>\n",
 844 |        "    </tr>\n",
 845 |        "    <tr>\n",
 846 |        "      <th>2</th>\n",
 847 |        "      <td>48</td>\n",
 848 |        "      <td>48</td>\n",
 849 |        "      <td>25</td>\n",
 850 |        "      <td>14</td>\n",
 851 |        "    </tr>\n",
 852 |        "    <tr>\n",
 853 |        "      <th>3</th>\n",
 854 |        "      <td>16</td>\n",
 855 |        "      <td>10</td>\n",
 856 |        "      <td>0</td>\n",
 857 |        "      <td>0</td>\n",
 858 |        "    </tr>\n",
 859 |        "    <tr>\n",
 860 |        "      <th>4</th>\n",
 861 |        "      <td>16</td>\n",
 862 |        "      <td>15</td>\n",
 863 |        "      <td>2</td>\n",
 864 |        "      <td>0</td>\n",
 865 |        "    </tr>\n",
 866 |        "    <tr>\n",
 867 |        "      <th>...</th>\n",
 868 |        "      <td>...</td>\n",
 869 |        "      <td>...</td>\n",
 870 |        "      <td>...</td>\n",
 871 |        "      <td>...</td>\n",
 872 |        "    </tr>\n",
 873 |        "    <tr>\n",
 874 |        "      <th>118</th>\n",
 875 |        "      <td>12</td>\n",
 876 |        "      <td>1</td>\n",
 877 |        "      <td>1</td>\n",
 878 |        "      <td>0</td>\n",
 879 |        "    </tr>\n",
 880 |        "    <tr>\n",
 881 |        "      <th>119</th>\n",
 882 |        "      <td>6</td>\n",
 883 |        "      <td>0</td>\n",
 884 |        "      <td>0</td>\n",
 885 |        "      <td>0</td>\n",
 886 |        "    </tr>\n",
 887 |        "    <tr>\n",
 888 |        "      <th>120</th>\n",
 889 |        "      <td>110</td>\n",
 890 |        "      <td>6</td>\n",
 891 |        "      <td>0</td>\n",
 892 |        "      <td>0</td>\n",
 893 |        "    </tr>\n",
 894 |        "    <tr>\n",
 895 |        "      <th>121</th>\n",
 896 |        "      <td>67</td>\n",
 897 |        "      <td>2</td>\n",
 898 |        "      <td>0</td>\n",
 899 |        "      <td>0</td>\n",
 900 |        "    </tr>\n",
 901 |        "    <tr>\n",
 902 |        "      <th>122</th>\n",
 903 |        "      <td>3</td>\n",
 904 |        "      <td>1</td>\n",
 905 |        "      <td>1</td>\n",
 906 |        "      <td>0</td>\n",
 907 |        "    </tr>\n",
 908 |        "  </tbody>\n",
 909 |        "</table>\n",
 910 |        "<p>123 rows × 4 columns</p>\n",
 911 |        "</div>"
 912 |       ],
 913 |       "text/plain": [
 914 |        "     持续一年期的交易企业个数  持续二年期的交易企业个数  持续三年期的交易企业个数  持续四年前的交易企业个数\n",
 915 |        "0             179            51            51            71\n",
 916 |        "1            1147           268           121            43\n",
 917 |        "2              48            48            25            14\n",
 918 |        "3              16            10             0             0\n",
 919 |        "4              16            15             2             0\n",
 920 |        "..            ...           ...           ...           ...\n",
 921 |        "118            12             1             1             0\n",
 922 |        "119             6             0             0             0\n",
 923 |        "120           110             6             0             0\n",
 924 |        "121            67             2             0             0\n",
 925 |        "122             3             1             1             0\n",
 926 |        "\n",
 927 |        "[123 rows x 4 columns]"
 928 |       ]
 929 |      },
 930 |      "execution_count": 231,
 931 |      "metadata": {},
 932 |      "output_type": "execute_result"
 933 |     }
 934 |    ],
 935 |    "source": [
 936 |     "da2= {'持续一年期的交易企业个数':deal1,\n",
 937 |     "     '持续二年期的交易企业个数': deal2,\n",
 938 |     "     '持续三年期的交易企业个数': deal3,\n",
 939 |     "     '持续四年前的交易企业个数':deal4\n",
 940 |     "     }\n",
 941 |     "\n",
 942 |     "xx = pd.DataFrame(data=da2)\n",
 943 |     "xx "
 944 |    ]
 945 |   },
 946 |   {
 947 |    "cell_type": "code",
 948 |    "execution_count": 300,
 949 |    "metadata": {},
 950 |    "outputs": [],
 951 |    "source": [
 952 |     "xx.to_csv('下游持续交易企业.csv',encoding='gbk')"
 953 |    ]
 954 |   },
 955 |   {
 956 |    "cell_type": "code",
 957 |    "execution_count": null,
 958 |    "metadata": {},
 959 |    "outputs": [],
 960 |    "source": []
 961 |   },
 962 |   {
 963 |    "cell_type": "code",
 964 |    "execution_count": 233,
 965 |    "metadata": {},
 966 |    "outputs": [],
 967 |    "source": [
 968 |     "in_y=[]\n",
 969 |     "for num in range(1,124):      # 遍历目标企业\n",
 970 |     "    l_1 = 0\n",
 971 |     "    l_2 = 0\n",
 972 |     "    l_3 = 0       # 一年、两年、三年、四年的交易方\n",
 973 |     "    l_4 = 0\n",
 974 |     "    l_5 = 0\n",
 975 |     "\n",
 976 |     "    id1 = 'E'+str(num)\n",
 977 |     "    a = input1[input1['企业代号']==id1]\n",
 978 |     "    a = a.reset_index(drop=True)\n",
 979 |     "    other = np.unique(a['销方单位代号'])    # 交易方代号的唯一值\n",
 980 |     "    \n",
 981 |     "    year = a['开票日期'][len(a)-1].year - a['开票日期'][0].year+1  \n",
 982 |     "    in_y.append(year)\n",
 983 |     "\n",
 984 |     "\n",
 985 |     "\n",
 986 |     "out_y=[]\n",
 987 |     "for num in range(1,124):      # 遍历目标企业\n",
 988 |     "    l_1 = 0\n",
 989 |     "    l_2 = 0\n",
 990 |     "    l_3 = 0       # 一年、两年、三年、四年的交易方\n",
 991 |     "    l_4 = 0\n",
 992 |     "\n",
 993 |     "    id1 = 'E'+str(num)\n",
 994 |     "    a = output1[output1['企业代号']==id1]\n",
 995 |     "    a = a.reset_index(drop=True)\n",
 996 |     "    other = np.unique(a['购方单位代号'])    # 交易方代号的唯一值\n",
 997 |     "    \n",
 998 |     "    year = a['开票日期'][len(a)-1].year - a['开票日期'][0].year+1  \n",
 999 |     "    out_y.append(year)"
1000 |    ]
1001 |   },
1002 |   {
1003 |    "cell_type": "code",
1004 |    "execution_count": null,
1005 |    "metadata": {},
1006 |    "outputs": [],
1007 |    "source": []
1008 |   },
1009 |   {
1010 |    "cell_type": "code",
1011 |    "execution_count": 245,
1012 |    "metadata": {},
1013 |    "outputs": [],
1014 |    "source": [
1015 |     "new_in = input1[(input1['开票日期']<'2020')]    # 2020年之前的进项数据\n",
1016 |     "new_out = output1[(output1['开票日期']<'2020')]"
1017 |    ]
1018 |   },
1019 |   {
1020 |    "cell_type": "code",
1021 |    "execution_count": 246,
1022 |    "metadata": {},
1023 |    "outputs": [
1024 |     {
1025 |      "data": {
1026 |       "text/html": [
1027 |        "<div>\n",
1028 |        "<style scoped>\n",
1029 |        "    .dataframe tbody tr th:only-of-type {\n",
1030 |        "        vertical-align: middle;\n",
1031 |        "    }\n",
1032 |        "\n",
1033 |        "    .dataframe tbody tr th {\n",
1034 |        "        vertical-align: top;\n",
1035 |        "    }\n",
1036 |        "\n",
1037 |        "    .dataframe thead th {\n",
1038 |        "        text-align: right;\n",
1039 |        "    }\n",
1040 |        "</style>\n",
1041 |        "<table border=\"1\" class=\"dataframe\">\n",
1042 |        "  <thead>\n",
1043 |        "    <tr style=\"text-align: right;\">\n",
1044 |        "      <th></th>\n",
1045 |        "      <th>企业代号</th>\n",
1046 |        "      <th>发票号码</th>\n",
1047 |        "      <th>开票日期</th>\n",
1048 |        "      <th>销方单位代号</th>\n",
1049 |        "      <th>金额</th>\n",
1050 |        "      <th>税额</th>\n",
1051 |        "      <th>价税合计</th>\n",
1052 |        "      <th>发票状态</th>\n",
1053 |        "    </tr>\n",
1054 |        "  </thead>\n",
1055 |        "  <tbody>\n",
1056 |        "    <tr>\n",
1057 |        "      <th>0</th>\n",
1058 |        "      <td>E1</td>\n",
1059 |        "      <td>3390939</td>\n",
1060 |        "      <td>2017-07-18</td>\n",
1061 |        "      <td>A00297</td>\n",
1062 |        "      <td>-943.40</td>\n",
1063 |        "      <td>-56.60</td>\n",
1064 |        "      <td>-1000.00</td>\n",
1065 |        "      <td>有效发票</td>\n",
1066 |        "    </tr>\n",
1067 |        "    <tr>\n",
1068 |        "      <th>1</th>\n",
1069 |        "      <td>E1</td>\n",
1070 |        "      <td>3390940</td>\n",
1071 |        "      <td>2017-07-18</td>\n",
1072 |        "      <td>A00297</td>\n",
1073 |        "      <td>-4780.24</td>\n",
1074 |        "      <td>-286.81</td>\n",
1075 |        "      <td>-5067.05</td>\n",
1076 |        "      <td>有效发票</td>\n",
1077 |        "    </tr>\n",
1078 |        "    <tr>\n",
1079 |        "      <th>2</th>\n",
1080 |        "      <td>E1</td>\n",
1081 |        "      <td>3390941</td>\n",
1082 |        "      <td>2017-07-18</td>\n",
1083 |        "      <td>A00297</td>\n",
1084 |        "      <td>943.40</td>\n",
1085 |        "      <td>56.60</td>\n",
1086 |        "      <td>1000.00</td>\n",
1087 |        "      <td>有效发票</td>\n",
1088 |        "    </tr>\n",
1089 |        "    <tr>\n",
1090 |        "      <th>3</th>\n",
1091 |        "      <td>E1</td>\n",
1092 |        "      <td>3390942</td>\n",
1093 |        "      <td>2017-07-18</td>\n",
1094 |        "      <td>A00297</td>\n",
1095 |        "      <td>4780.24</td>\n",
1096 |        "      <td>286.81</td>\n",
1097 |        "      <td>5067.05</td>\n",
1098 |        "      <td>有效发票</td>\n",
1099 |        "    </tr>\n",
1100 |        "    <tr>\n",
1101 |        "      <th>4</th>\n",
1102 |        "      <td>E1</td>\n",
1103 |        "      <td>9902669</td>\n",
1104 |        "      <td>2017-08-07</td>\n",
1105 |        "      <td>A05061</td>\n",
1106 |        "      <td>326.21</td>\n",
1107 |        "      <td>9.79</td>\n",
1108 |        "      <td>336.00</td>\n",
1109 |        "      <td>有效发票</td>\n",
1110 |        "    </tr>\n",
1111 |        "    <tr>\n",
1112 |        "      <th>...</th>\n",
1113 |        "      <td>...</td>\n",
1114 |        "      <td>...</td>\n",
1115 |        "      <td>...</td>\n",
1116 |        "      <td>...</td>\n",
1117 |        "      <td>...</td>\n",
1118 |        "      <td>...</td>\n",
1119 |        "      <td>...</td>\n",
1120 |        "      <td>...</td>\n",
1121 |        "    </tr>\n",
1122 |        "    <tr>\n",
1123 |        "      <th>203333</th>\n",
1124 |        "      <td>E122</td>\n",
1125 |        "      <td>42055639</td>\n",
1126 |        "      <td>2019-03-25</td>\n",
1127 |        "      <td>A13332</td>\n",
1128 |        "      <td>17636.09</td>\n",
1129 |        "      <td>1058.17</td>\n",
1130 |        "      <td>18694.26</td>\n",
1131 |        "      <td>有效发票</td>\n",
1132 |        "    </tr>\n",
1133 |        "    <tr>\n",
1134 |        "      <th>203334</th>\n",
1135 |        "      <td>E122</td>\n",
1136 |        "      <td>54706234</td>\n",
1137 |        "      <td>2019-04-17</td>\n",
1138 |        "      <td>A08967</td>\n",
1139 |        "      <td>223.30</td>\n",
1140 |        "      <td>6.70</td>\n",
1141 |        "      <td>230.00</td>\n",
1142 |        "      <td>有效发票</td>\n",
1143 |        "    </tr>\n",
1144 |        "    <tr>\n",
1145 |        "      <th>203336</th>\n",
1146 |        "      <td>E123</td>\n",
1147 |        "      <td>38493295</td>\n",
1148 |        "      <td>2017-12-15</td>\n",
1149 |        "      <td>A03624</td>\n",
1150 |        "      <td>264.15</td>\n",
1151 |        "      <td>15.85</td>\n",
1152 |        "      <td>280.00</td>\n",
1153 |        "      <td>有效发票</td>\n",
1154 |        "    </tr>\n",
1155 |        "    <tr>\n",
1156 |        "      <th>203337</th>\n",
1157 |        "      <td>E123</td>\n",
1158 |        "      <td>95472001</td>\n",
1159 |        "      <td>2018-12-29</td>\n",
1160 |        "      <td>A03626</td>\n",
1161 |        "      <td>264.15</td>\n",
1162 |        "      <td>15.85</td>\n",
1163 |        "      <td>280.00</td>\n",
1164 |        "      <td>有效发票</td>\n",
1165 |        "    </tr>\n",
1166 |        "    <tr>\n",
1167 |        "      <th>203338</th>\n",
1168 |        "      <td>E123</td>\n",
1169 |        "      <td>54469883</td>\n",
1170 |        "      <td>2019-12-18</td>\n",
1171 |        "      <td>A03626</td>\n",
1172 |        "      <td>264.15</td>\n",
1173 |        "      <td>15.85</td>\n",
1174 |        "      <td>280.00</td>\n",
1175 |        "      <td>有效发票</td>\n",
1176 |        "    </tr>\n",
1177 |        "  </tbody>\n",
1178 |        "</table>\n",
1179 |        "<p>198371 rows × 8 columns</p>\n",
1180 |        "</div>"
1181 |       ],
1182 |       "text/plain": [
1183 |        "        企业代号      发票号码       开票日期  销方单位代号        金额       税额      价税合计  发票状态\n",
1184 |        "0         E1   3390939 2017-07-18  A00297   -943.40   -56.60  -1000.00  有效发票\n",
1185 |        "1         E1   3390940 2017-07-18  A00297  -4780.24  -286.81  -5067.05  有效发票\n",
1186 |        "2         E1   3390941 2017-07-18  A00297    943.40    56.60   1000.00  有效发票\n",
1187 |        "3         E1   3390942 2017-07-18  A00297   4780.24   286.81   5067.05  有效发票\n",
1188 |        "4         E1   9902669 2017-08-07  A05061    326.21     9.79    336.00  有效发票\n",
1189 |        "...      ...       ...        ...     ...       ...      ...       ...   ...\n",
1190 |        "203333  E122  42055639 2019-03-25  A13332  17636.09  1058.17  18694.26  有效发票\n",
1191 |        "203334  E122  54706234 2019-04-17  A08967    223.30     6.70    230.00  有效发票\n",
1192 |        "203336  E123  38493295 2017-12-15  A03624    264.15    15.85    280.00  有效发票\n",
1193 |        "203337  E123  95472001 2018-12-29  A03626    264.15    15.85    280.00  有效发票\n",
1194 |        "203338  E123  54469883 2019-12-18  A03626    264.15    15.85    280.00  有效发票\n",
1195 |        "\n",
1196 |        "[198371 rows x 8 columns]"
1197 |       ]
1198 |      },
1199 |      "execution_count": 246,
1200 |      "metadata": {},
1201 |      "output_type": "execute_result"
1202 |     }
1203 |    ],
1204 |    "source": [
1205 |     "new_in"
1206 |    ]
1207 |   },
1208 |   {
1209 |    "cell_type": "code",
1210 |    "execution_count": 292,
1211 |    "metadata": {},
1212 |    "outputs": [],
1213 |    "source": [
1214 |     "ur = []\n",
1215 |     "\n",
1216 |     "dd = []\n",
1217 |     "for num in range(1,124):      # 遍历目标企业\n",
1218 |     "    \n",
1219 |     "    id1 = 'E'+str(num)\n",
1220 |     "    a = new_in[new_in['企业代号']==id1]\n",
1221 |     "    a = a.reset_index(drop=True)\n",
1222 |     "    \n",
1223 |     "    end_1 = a['开票日期'][len(a)-1].year\n",
1224 |     "    begin_1 = a['开票日期'][0].year\n",
1225 |     "    \n",
1226 |     "    begin_ji_1 = a[(a['开票日期']>str(begin_1))&(a['开票日期']<str(begin_1+1))]['金额'].sum()\n",
1227 |     "    end_ji_1 =  a[(a['开票日期']>str(end_1))&(a['开票日期']<str(end_1+1))]['金额'].sum()\n",
1228 |     "    \n",
1229 |     "    \n",
1230 |     "    b = new_out[new_out['企业代号']==id1]\n",
1231 |     "    b = b.reset_index(drop=True)\n",
1232 |     "    \n",
1233 |     "    end_2 = b['开票日期'][len(b)-1].year\n",
1234 |     "    begin_2 = b['开票日期'][0].year\n",
1235 |     "    \n",
1236 |     "    begin_ji_2 = b[(b['开票日期']>str(begin_2))&(b['开票日期']<str(begin_2+1))]['金额'].sum()\n",
1237 |     "    end_ji_2 =  b[(b['开票日期']>str(end_2))&(b['开票日期']<str(end_2+1))]['金额'].sum()\n",
1238 |     "    \n",
1239 |     "    up_rate = (end_ji_2-end_ji_1)/(begin_ji_2-begin_ji_1)\n",
1240 |     "    \n",
1241 |     "    d = (end_ji_2-end_ji_1)-(begin_ji_2-begin_ji_1)\n",
1242 |     "    \n",
1243 |     "    \n",
1244 |     "    ur.append(up_rate)\n",
1245 |     "    dd.append(d)"
1246 |    ]
1247 |   },
1248 |   {
1249 |    "cell_type": "code",
1250 |    "execution_count": 293,
1251 |    "metadata": {},
1252 |    "outputs": [
1253 |     {
1254 |      "data": {
1255 |       "text/plain": [
1256 |        "[-193872135.96000051,\n",
1257 |        " 110302536.47999997,\n",
1258 |        " -115477286.08000003,\n",
1259 |        " -1168509293.45,\n",
1260 |        " 4068217.1499999883,\n",
1261 |        " 14520912.319999982,\n",
1262 |        " -170352223.81,\n",
1263 |        " 10175963.700000003,\n",
1264 |        " 8701373.75999999,\n",
1265 |        " 82858784.61000001,\n",
1266 |        " -38346246.26000001,\n",
1267 |        " -84557485.89000002,\n",
1268 |        " 17290905.08,\n",
1269 |        " 8017782.599999994,\n",
1270 |        " 28666792.4,\n",
1271 |        " 39872630.50000001,\n",
1272 |        " 10825143.39,\n",
1273 |        " 17393819.630000006,\n",
1274 |        " 457386.0400000019,\n",
1275 |        " 4408596.540000007,\n",
1276 |        " 9020452.639999993,\n",
1277 |        " 34495523.8,\n",
1278 |        " -6130097.840000002,\n",
1279 |        " 21065382.97,\n",
1280 |        " 3950781.0299999993,\n",
1281 |        " 801968.4499999988,\n",
1282 |        " 340587.8900000041,\n",
1283 |        " 19643668.89,\n",
1284 |        " 11138949.26,\n",
1285 |        " 2738199.3100000005,\n",
1286 |        " 7131326.480000002,\n",
1287 |        " 11818843.080000004,\n",
1288 |        " -1247606.5799999963,\n",
1289 |        " -1442409.789999997,\n",
1290 |        " 4954392.8100000005,\n",
1291 |        " 5859723.15,\n",
1292 |        " 20100.5100000035,\n",
1293 |        " 3241096.44999999,\n",
1294 |        " 13935775.469999997,\n",
1295 |        " 13206723.029999997,\n",
1296 |        " 12254350.030000005,\n",
1297 |        " 12910420.96,\n",
1298 |        " 1390239.3199999994,\n",
1299 |        " 899638.66,\n",
1300 |        " -697757.9200000023,\n",
1301 |        " 1283506.089999996,\n",
1302 |        " 1285307.1699999971,\n",
1303 |        " 17195806.14,\n",
1304 |        " -4707428.380000005,\n",
1305 |        " 6781297.75,\n",
1306 |        " 5553169.2200000025,\n",
1307 |        " 1095999.810000001,\n",
1308 |        " 244683.3399999952,\n",
1309 |        " 3650147.2699999977,\n",
1310 |        " -3163800.209999998,\n",
1311 |        " 590087.4299999978,\n",
1312 |        " -2307020.6000000075,\n",
1313 |        " 4623582.119999999,\n",
1314 |        " 2076239.5500000007,\n",
1315 |        " 2762867.1399999997,\n",
1316 |        " -1426691.210000001,\n",
1317 |        " -1325522.4999999995,\n",
1318 |        " -7595933.389999997,\n",
1319 |        " 412503.1499999999,\n",
1320 |        " 745267.0700000005,\n",
1321 |        " 1573358.2900000003,\n",
1322 |        " 2189387.6499999994,\n",
1323 |        " -2731449.09,\n",
1324 |        " 2661870.58,\n",
1325 |        " -2036647.4900000012,\n",
1326 |        " 5842485.550000002,\n",
1327 |        " 1453197.4200000004,\n",
1328 |        " -1344863.8400000003,\n",
1329 |        " 1388223.6600000001,\n",
1330 |        " -1700637.8,\n",
1331 |        " 940249.3899999999,\n",
1332 |        " -759119.19,\n",
1333 |        " -2691870.8800000004,\n",
1334 |        " 1034964.7000000001,\n",
1335 |        " 3297244.3599999994,\n",
1336 |        " 182894.30999999982,\n",
1337 |        " 118211.17000000016,\n",
1338 |        " -11859813.95,\n",
1339 |        " 641060.9200000002,\n",
1340 |        " 509292.93,\n",
1341 |        " -606338.2799999999,\n",
1342 |        " 674008.5799999998,\n",
1343 |        " 181422.32999999978,\n",
1344 |        " 2630392.2200000007,\n",
1345 |        " 426767.62,\n",
1346 |        " 267744.8800000001,\n",
1347 |        " 1226750.25,\n",
1348 |        " 190487.10999999996,\n",
1349 |        " 296547.19999999995,\n",
1350 |        " -173150.46999999997,\n",
1351 |        " 1348697.7599999998,\n",
1352 |        " 428086.2799999998,\n",
1353 |        " -106852.63000000012,\n",
1354 |        " -1114717.3699999999,\n",
1355 |        " -111912.90000000005,\n",
1356 |        " -119859.56999999999,\n",
1357 |        " 43268.34999999998,\n",
1358 |        " 49319.53999999992,\n",
1359 |        " 103233.00999999998,\n",
1360 |        " -134853.55999999997,\n",
1361 |        " 139940.22999999998,\n",
1362 |        " 600297.72,\n",
1363 |        " -123849.10999999999,\n",
1364 |        " 274393.5,\n",
1365 |        " 21642.649999999998,\n",
1366 |        " -271144.93,\n",
1367 |        " 208206.56999999983,\n",
1368 |        " -82420.22,\n",
1369 |        " -356779.9,\n",
1370 |        " 35728.159999999996,\n",
1371 |        " -75814.26,\n",
1372 |        " 211072.46000000008,\n",
1373 |        " -141118.15,\n",
1374 |        " -68619.21999999999,\n",
1375 |        " 8830.94999999999,\n",
1376 |        " 690652.18,\n",
1377 |        " -27347.289999999994,\n",
1378 |        " 17453.840000000004]"
1379 |       ]
1380 |      },
1381 |      "execution_count": 293,
1382 |      "metadata": {},
1383 |      "output_type": "execute_result"
1384 |     }
1385 |    ],
1386 |    "source": [
1387 |     "dd"
1388 |    ]
1389 |   },
1390 |   {
1391 |    "cell_type": "code",
1392 |    "execution_count": 294,
1393 |    "metadata": {},
1394 |    "outputs": [
1395 |     {
1396 |      "data": {
1397 |       "text/html": [
1398 |        "<div>\n",
1399 |        "<style scoped>\n",
1400 |        "    .dataframe tbody tr th:only-of-type {\n",
1401 |        "        vertical-align: middle;\n",
1402 |        "    }\n",
1403 |        "\n",
1404 |        "    .dataframe tbody tr th {\n",
1405 |        "        vertical-align: top;\n",
1406 |        "    }\n",
1407 |        "\n",
1408 |        "    .dataframe thead th {\n",
1409 |        "        text-align: right;\n",
1410 |        "    }\n",
1411 |        "</style>\n",
1412 |        "<table border=\"1\" class=\"dataframe\">\n",
1413 |        "  <thead>\n",
1414 |        "    <tr style=\"text-align: right;\">\n",
1415 |        "      <th></th>\n",
1416 |        "      <th>绝对数变化</th>\n",
1417 |        "      <th>比例变化</th>\n",
1418 |        "    </tr>\n",
1419 |        "  </thead>\n",
1420 |        "  <tbody>\n",
1421 |        "    <tr>\n",
1422 |        "      <th>0</th>\n",
1423 |        "      <td>-1.938721e+08</td>\n",
1424 |        "      <td>1.720614</td>\n",
1425 |        "    </tr>\n",
1426 |        "    <tr>\n",
1427 |        "      <th>1</th>\n",
1428 |        "      <td>1.103025e+08</td>\n",
1429 |        "      <td>2.197674</td>\n",
1430 |        "    </tr>\n",
1431 |        "    <tr>\n",
1432 |        "      <th>2</th>\n",
1433 |        "      <td>-1.154773e+08</td>\n",
1434 |        "      <td>0.516353</td>\n",
1435 |        "    </tr>\n",
1436 |        "    <tr>\n",
1437 |        "      <th>3</th>\n",
1438 |        "      <td>-1.168509e+09</td>\n",
1439 |        "      <td>0.053642</td>\n",
1440 |        "    </tr>\n",
1441 |        "    <tr>\n",
1442 |        "      <th>4</th>\n",
1443 |        "      <td>4.068217e+06</td>\n",
1444 |        "      <td>85.227087</td>\n",
1445 |        "    </tr>\n",
1446 |        "    <tr>\n",
1447 |        "      <th>...</th>\n",
1448 |        "      <td>...</td>\n",
1449 |        "      <td>...</td>\n",
1450 |        "    </tr>\n",
1451 |        "    <tr>\n",
1452 |        "      <th>118</th>\n",
1453 |        "      <td>-6.861922e+04</td>\n",
1454 |        "      <td>6.999117</td>\n",
1455 |        "    </tr>\n",
1456 |        "    <tr>\n",
1457 |        "      <th>119</th>\n",
1458 |        "      <td>8.830950e+03</td>\n",
1459 |        "      <td>1.139033</td>\n",
1460 |        "    </tr>\n",
1461 |        "    <tr>\n",
1462 |        "      <th>120</th>\n",
1463 |        "      <td>6.906522e+05</td>\n",
1464 |        "      <td>-0.075122</td>\n",
1465 |        "    </tr>\n",
1466 |        "    <tr>\n",
1467 |        "      <th>121</th>\n",
1468 |        "      <td>-2.734729e+04</td>\n",
1469 |        "      <td>-0.681496</td>\n",
1470 |        "    </tr>\n",
1471 |        "    <tr>\n",
1472 |        "      <th>122</th>\n",
1473 |        "      <td>1.745384e+04</td>\n",
1474 |        "      <td>1.824361</td>\n",
1475 |        "    </tr>\n",
1476 |        "  </tbody>\n",
1477 |        "</table>\n",
1478 |        "<p>123 rows × 2 columns</p>\n",
1479 |        "</div>"
1480 |       ],
1481 |       "text/plain": [
1482 |        "            绝对数变化       比例变化\n",
1483 |        "0   -1.938721e+08   1.720614\n",
1484 |        "1    1.103025e+08   2.197674\n",
1485 |        "2   -1.154773e+08   0.516353\n",
1486 |        "3   -1.168509e+09   0.053642\n",
1487 |        "4    4.068217e+06  85.227087\n",
1488 |        "..            ...        ...\n",
1489 |        "118 -6.861922e+04   6.999117\n",
1490 |        "119  8.830950e+03   1.139033\n",
1491 |        "120  6.906522e+05  -0.075122\n",
1492 |        "121 -2.734729e+04  -0.681496\n",
1493 |        "122  1.745384e+04   1.824361\n",
1494 |        "\n",
1495 |        "[123 rows x 2 columns]"
1496 |       ]
1497 |      },
1498 |      "execution_count": 294,
1499 |      "metadata": {},
1500 |      "output_type": "execute_result"
1501 |     }
1502 |    ],
1503 |    "source": [
1504 |     "data3 = {'绝对数变化':dd,\n",
1505 |     "        '比例变化':ur}\n",
1506 |     "df3 = pd.DataFrame(data=data3)\n",
1507 |     "df3"
1508 |    ]
1509 |   },
1510 |   {
1511 |    "cell_type": "code",
1512 |    "execution_count": 297,
1513 |    "metadata": {
1514 |     "scrolled": true
1515 |    },
1516 |    "outputs": [
1517 |     {
1518 |      "data": {
1519 |       "text/html": [
1520 |        "<div>\n",
1521 |        "<style scoped>\n",
1522 |        "    .dataframe tbody tr th:only-of-type {\n",
1523 |        "        vertical-align: middle;\n",
1524 |        "    }\n",
1525 |        "\n",
1526 |        "    .dataframe tbody tr th {\n",
1527 |        "        vertical-align: top;\n",
1528 |        "    }\n",
1529 |        "\n",
1530 |        "    .dataframe thead th {\n",
1531 |        "        text-align: right;\n",
1532 |        "    }\n",
1533 |        "</style>\n",
1534 |        "<table border=\"1\" class=\"dataframe\">\n",
1535 |        "  <thead>\n",
1536 |        "    <tr style=\"text-align: right;\">\n",
1537 |        "      <th></th>\n",
1538 |        "      <th>绝对数变化</th>\n",
1539 |        "      <th>比例变化</th>\n",
1540 |        "      <th>是否扭亏为盈利</th>\n",
1541 |        "      <th>是否变为亏损</th>\n",
1542 |        "    </tr>\n",
1543 |        "  </thead>\n",
1544 |        "  <tbody>\n",
1545 |        "    <tr>\n",
1546 |        "      <th>0</th>\n",
1547 |        "      <td>-1.938721e+08</td>\n",
1548 |        "      <td>1.720614</td>\n",
1549 |        "      <td>0.0</td>\n",
1550 |        "      <td>0.0</td>\n",
1551 |        "    </tr>\n",
1552 |        "    <tr>\n",
1553 |        "      <th>1</th>\n",
1554 |        "      <td>1.103025e+08</td>\n",
1555 |        "      <td>2.197674</td>\n",
1556 |        "      <td>0.0</td>\n",
1557 |        "      <td>0.0</td>\n",
1558 |        "    </tr>\n",
1559 |        "    <tr>\n",
1560 |        "      <th>2</th>\n",
1561 |        "      <td>-1.154773e+08</td>\n",
1562 |        "      <td>0.516353</td>\n",
1563 |        "      <td>0.0</td>\n",
1564 |        "      <td>0.0</td>\n",
1565 |        "    </tr>\n",
1566 |        "    <tr>\n",
1567 |        "      <th>3</th>\n",
1568 |        "      <td>-1.168509e+09</td>\n",
1569 |        "      <td>0.053642</td>\n",
1570 |        "      <td>0.0</td>\n",
1571 |        "      <td>0.0</td>\n",
1572 |        "    </tr>\n",
1573 |        "    <tr>\n",
1574 |        "      <th>4</th>\n",
1575 |        "      <td>4.068217e+06</td>\n",
1576 |        "      <td>85.227087</td>\n",
1577 |        "      <td>0.0</td>\n",
1578 |        "      <td>0.0</td>\n",
1579 |        "    </tr>\n",
1580 |        "    <tr>\n",
1581 |        "      <th>...</th>\n",
1582 |        "      <td>...</td>\n",
1583 |        "      <td>...</td>\n",
1584 |        "      <td>...</td>\n",
1585 |        "      <td>...</td>\n",
1586 |        "    </tr>\n",
1587 |        "    <tr>\n",
1588 |        "      <th>118</th>\n",
1589 |        "      <td>-6.861922e+04</td>\n",
1590 |        "      <td>6.999117</td>\n",
1591 |        "      <td>0.0</td>\n",
1592 |        "      <td>0.0</td>\n",
1593 |        "    </tr>\n",
1594 |        "    <tr>\n",
1595 |        "      <th>119</th>\n",
1596 |        "      <td>8.830950e+03</td>\n",
1597 |        "      <td>1.139033</td>\n",
1598 |        "      <td>0.0</td>\n",
1599 |        "      <td>0.0</td>\n",
1600 |        "    </tr>\n",
1601 |        "    <tr>\n",
1602 |        "      <th>120</th>\n",
1603 |        "      <td>6.906522e+05</td>\n",
1604 |        "      <td>-0.075122</td>\n",
1605 |        "      <td>1.0</td>\n",
1606 |        "      <td>0.0</td>\n",
1607 |        "    </tr>\n",
1608 |        "    <tr>\n",
1609 |        "      <th>121</th>\n",
1610 |        "      <td>-2.734729e+04</td>\n",
1611 |        "      <td>-0.681496</td>\n",
1612 |        "      <td>0.0</td>\n",
1613 |        "      <td>1.0</td>\n",
1614 |        "    </tr>\n",
1615 |        "    <tr>\n",
1616 |        "      <th>122</th>\n",
1617 |        "      <td>1.745384e+04</td>\n",
1618 |        "      <td>1.824361</td>\n",
1619 |        "      <td>0.0</td>\n",
1620 |        "      <td>0.0</td>\n",
1621 |        "    </tr>\n",
1622 |        "  </tbody>\n",
1623 |        "</table>\n",
1624 |        "<p>123 rows × 4 columns</p>\n",
1625 |        "</div>"
1626 |       ],
1627 |       "text/plain": [
1628 |        "            绝对数变化       比例变化  是否扭亏为盈利  是否变为亏损\n",
1629 |        "0   -1.938721e+08   1.720614      0.0     0.0\n",
1630 |        "1    1.103025e+08   2.197674      0.0     0.0\n",
1631 |        "2   -1.154773e+08   0.516353      0.0     0.0\n",
1632 |        "3   -1.168509e+09   0.053642      0.0     0.0\n",
1633 |        "4    4.068217e+06  85.227087      0.0     0.0\n",
1634 |        "..            ...        ...      ...     ...\n",
1635 |        "118 -6.861922e+04   6.999117      0.0     0.0\n",
1636 |        "119  8.830950e+03   1.139033      0.0     0.0\n",
1637 |        "120  6.906522e+05  -0.075122      1.0     0.0\n",
1638 |        "121 -2.734729e+04  -0.681496      0.0     1.0\n",
1639 |        "122  1.745384e+04   1.824361      0.0     0.0\n",
1640 |        "\n",
1641 |        "[123 rows x 4 columns]"
1642 |       ]
1643 |      },
1644 |      "execution_count": 297,
1645 |      "metadata": {},
1646 |      "output_type": "execute_result"
1647 |     }
1648 |    ],
1649 |    "source": [
1650 |     "for i in range(len(df3)):\n",
1651 |     "    if (df3.loc[i,'绝对数变化']>0) & (df3.loc[i,'比例变化']<0):     # 说明扭亏为盈\n",
1652 |     "        df3.loc[i,'是否扭亏为盈利']=1\n",
1653 |     "    else:\n",
1654 |     "        df3.loc[i,'是否扭亏为盈利']=0\n",
1655 |     "\n",
1656 |     "for i in range(len(df3)):\n",
1657 |     "    if (df3.loc[i,'绝对数变化']<0) & (df3.loc[i,'比例变化']<0):     # 说明扭亏为盈\n",
1658 |     "        df3.loc[i,'是否变为亏损']=1\n",
1659 |     "    else:\n",
1660 |     "        df3.loc[i,'是否变为亏损']=0        \n",
1661 |     "\n",
1662 |     "df3"
1663 |    ]
1664 |   },
1665 |   {
1666 |    "cell_type": "code",
1667 |    "execution_count": 299,
1668 |    "metadata": {},
1669 |    "outputs": [],
1670 |    "source": [
1671 |     "df3.to_csv('发展程度.csv',encoding='gbk')"
1672 |    ]
1673 |   },
1674 |   {
1675 |    "cell_type": "code",
1676 |    "execution_count": 290,
1677 |    "metadata": {},
1678 |    "outputs": [],
1679 |    "source": [
1680 |     "num=5\n",
1681 |     "id1 = 'E'+str(num)\n",
1682 |     "a = new_in[new_in['企业代号']==id1]\n",
1683 |     "a = a.reset_index(drop=True)\n",
1684 |     "    \n",
1685 |     "end_1 = a['开票日期'][len(a)-1].year\n",
1686 |     "begin_1 = a['开票日期'][0].year\n",
1687 |     "    \n",
1688 |     "begin_ji_1 = a[(a['开票日期']>str(begin_1))&(a['开票日期']<str(begin_1+1))]['金额'].sum()\n",
1689 |     "end_ji_1 =  a[(a['开票日期']>str(end_1))&(a['开票日期']<str(end_1+1))]['金额'].sum()\n",
1690 |     "    \n",
1691 |     "    \n",
1692 |     "b = new_out[new_out['企业代号']==id1]\n",
1693 |     "b = b.reset_index(drop=True)\n",
1694 |     "    \n",
1695 |     "end_2 = b['开票日期'][len(b)-1].year\n",
1696 |     "begin_2 = b['开票日期'][0].year\n",
1697 |     "    \n",
1698 |     "begin_ji_2 = b[(b['开票日期']>str(begin_2))&(b['开票日期']<str(begin_2+1))]['金额'].sum()\n",
1699 |     "end_ji_2 =  b[(b['开票日期']>str(end_2))&(b['开票日期']<str(end_2+1))]['金额'].sum()\n",
1700 |     "\n",
1701 |     "up_rate = (end_ji_2-end_ji_1)/(begin_ji_2-begin_ji_1)"
1702 |    ]
1703 |   },
1704 |   {
1705 |    "cell_type": "code",
1706 |    "execution_count": 291,
1707 |    "metadata": {},
1708 |    "outputs": [
1709 |     {
1710 |      "name": "stdout",
1711 |      "output_type": "stream",
1712 |      "text": [
1713 |       "4116517.7299999893\n",
1714 |       "48300.580000001006\n"
1715 |      ]
1716 |     }
1717 |    ],
1718 |    "source": [
1719 |     "print(end_ji_2-end_ji_1)\n",
1720 |     "print(begin_ji_2-begin_ji_1)"
1721 |    ]
1722 |   },
1723 |   {
1724 |    "cell_type": "code",
1725 |    "execution_count": 289,
1726 |    "metadata": {},
1727 |    "outputs": [
1728 |     {
1729 |      "data": {
1730 |       "text/plain": [
1731 |        "[1.7206138607491175,\n",
1732 |        " 2.1976741755350835,\n",
1733 |        " 0.5163533480678486,\n",
1734 |        " 0.053642120805519077,\n",
1735 |        " 85.22708692110744,\n",
1736 |        " 6.220033757117115,\n",
1737 |        " 0.28299993853695593,\n",
1738 |        " 1.1903434951584118,\n",
1739 |        " 1.1026416281740918,\n",
1740 |        " 5.6952388287385975,\n",
1741 |        " 0.06224696926670617,\n",
1742 |        " 0.3142310613924136,\n",
1743 |        " 1.6246590416677933,\n",
1744 |        " 1.2608609677500382,\n",
1745 |        " 2.030952353418196,\n",
1746 |        " 4.42752647859875,\n",
1747 |        " 4.6091111208456725,\n",
1748 |        " 25.37000437751128,\n",
1749 |        " 1.2952080964666253,\n",
1750 |        " 3.448482477010922,\n",
1751 |        " -107.85542263470977,\n",
1752 |        " -68.36411555912315,\n",
1753 |        " -3.1526842431065614,\n",
1754 |        " 3.7508149740262886,\n",
1755 |        " 1.8719903885132894,\n",
1756 |        " -1.5351713542943943,\n",
1757 |        " -4.576462137815929,\n",
1758 |        " 7.404078615947699,\n",
1759 |        " 1.8563019203053552,\n",
1760 |        " 1.2348027347399602,\n",
1761 |        " 1.6791198336803776,\n",
1762 |        " 2.0636008405295763,\n",
1763 |        " 0.5125450991083275,\n",
1764 |        " 140.72763660986513,\n",
1765 |        " -11.283839443261392,\n",
1766 |        " 3.21411258457861,\n",
1767 |        " 0.9453293654883062,\n",
1768 |        " 1.3313401805724063,\n",
1769 |        " 7.452725580324382,\n",
1770 |        " 6.115626835894702,\n",
1771 |        " 4.989140651177328,\n",
1772 |        " 12.135349485779685,\n",
1773 |        " 1.1820756853858494,\n",
1774 |        " 6.562504223791024,\n",
1775 |        " -5.818097757171771,\n",
1776 |        " 12.069900028107975,\n",
1777 |        " 2.966145392466539,\n",
1778 |        " 5.250937640696781,\n",
1779 |        " 0.3892807875354888,\n",
1780 |        " 2.7108129964017462,\n",
1781 |        " 149.54003530827885,\n",
1782 |        " 2.928640924514602,\n",
1783 |        " 1.2334603990141317,\n",
1784 |        " 1.5594998109794656,\n",
1785 |        " 0.46138218820943555,\n",
1786 |        " 0.6080771865152791,\n",
1787 |        " -520.378261409993,\n",
1788 |        " 2.6319094838612047,\n",
1789 |        " 2.668089467441691,\n",
1790 |        " 16.648189248095253,\n",
1791 |        " 0.7516937403783559,\n",
1792 |        " 0.6407068582112135,\n",
1793 |        " 0.16375257516456432,\n",
1794 |        " 1.153526917922051,\n",
1795 |        " 3.181304820949343,\n",
1796 |        " 163.80308210318933,\n",
1797 |        " 5.055198895625344,\n",
1798 |        " 0.36464335940146825,\n",
1799 |        " 9.974805767095432,\n",
1800 |        " 0.059261051589976806,\n",
1801 |        " -0.2709463765525034,\n",
1802 |        " -13.392677548878696,\n",
1803 |        " 0.4947274866470568,\n",
1804 |        " 6.797415479219719,\n",
1805 |        " 0.21984318113850088,\n",
1806 |        " 2.752940948363574,\n",
1807 |        " 0.40213927290443346,\n",
1808 |        " 0.1871098157003494,\n",
1809 |        " -1.5078616268382043,\n",
1810 |        " -5.026949012353689,\n",
1811 |        " 1.5807090884942765,\n",
1812 |        " 1.3846505420473292,\n",
1813 |        " 3.545184777583607,\n",
1814 |        " 1.90864794440136,\n",
1815 |        " 3.3700166717840134,\n",
1816 |        " 0.22446511136396166,\n",
1817 |        " 3.983327703886272,\n",
1818 |        " 1.3939140560569714,\n",
1819 |        " -0.24416069302377294,\n",
1820 |        " 1.7143012299248843,\n",
1821 |        " 2.2548069280351783,\n",
1822 |        " 4.8187724433576635,\n",
1823 |        " 1.7732369258809357,\n",
1824 |        " 2.76189945427241,\n",
1825 |        " 0.762139235469635,\n",
1826 |        " 33.85250329329415,\n",
1827 |        " 2.842571435827089,\n",
1828 |        " 0.8056787332929423,\n",
1829 |        " -1.2156299914625928,\n",
1830 |        " 0.641697940845866,\n",
1831 |        " 0.4216714469252338,\n",
1832 |        " 0.9517159125112089,\n",
1833 |        " 1.0854157040280148,\n",
1834 |        " 2.299433945164303,\n",
1835 |        " 0.5724219467912264,\n",
1836 |        " 2.1574686630390443,\n",
1837 |        " 10.308934517607566,\n",
1838 |        " 0.03596442858317123,\n",
1839 |        " 7.229384822325518,\n",
1840 |        " 1.7883146301512365,\n",
1841 |        " -2.3730291699394095,\n",
1842 |        " 2.6999205095877516,\n",
1843 |        " -0.03891299889466099,\n",
1844 |        " -5.032003202822487,\n",
1845 |        " 4.706717461582195,\n",
1846 |        " 0.0661510030644933,\n",
1847 |        " 2.381499614196496,\n",
1848 |        " -0.33946290554118924,\n",
1849 |        " 6.999116995476569,\n",
1850 |        " 1.1390334045743837,\n",
1851 |        " -0.07512171533373088,\n",
1852 |        " -0.6814956279855656,\n",
1853 |        " 1.8243605644659273]"
1854 |       ]
1855 |      },
1856 |      "execution_count": 289,
1857 |      "metadata": {},
1858 |      "output_type": "execute_result"
1859 |     }
1860 |    ],
1861 |    "source": [
1862 |     "if "
1863 |    ]
1864 |   },
1865 |   {
1866 |    "cell_type": "markdown",
1867 |    "metadata": {},
1868 |    "source": [
1869 |     "# 第二问发票数据处理"
1870 |    ]
1871 |   },
1872 |   {
1873 |    "cell_type": "code",
1874 |    "execution_count": 1,
1875 |    "metadata": {},
1876 |    "outputs": [],
1877 |    "source": [
1878 |     "import pandas as pd\n",
1879 |     "import numpy as np\n",
1880 |     "import matplotlib.pyplot as plt\n",
1881 |     "from datetime import datetime\n",
1882 |     "import time\n",
1883 |     "\n",
1884 |     "input1 = pd.read_excel('附件2.xlsx',sheet_name='进项发票信息')\n",
1885 |     "output1 = pd.read_excel('附件2.xlsx',sheet_name='销项发票信息')"
1886 |    ]
1887 |   },
1888 |   {
1889 |    "cell_type": "code",
1890 |    "execution_count": 7,
1891 |    "metadata": {},
1892 |    "outputs": [],
1893 |    "source": [
1894 |     "# r_in=[]\n",
1895 |     "\n",
1896 |     "# for num in range(1,303):\n",
1897 |     "#     id1 = 'E'+str(num+123)\n",
1898 |     "#     tem = input1[input1['企业代号']==id1]\n",
1899 |     "#     all_num = tem.shape[0]\n",
1900 |     "#     fei_num = tem[tem['发票状态']=='作废发票'].shape[0]\n",
1901 |     "#     ratio = fei_num/all_num\n",
1902 |     "    \n",
1903 |     "#     r_in.append(ratio)\n",
1904 |     "    \n",
1905 |     "r_out=[]\n",
1906 |     "\n",
1907 |     "for num in range(1,303):\n",
1908 |     "    id1 = 'E'+str(num+123)\n",
1909 |     "    tem = output1[output1['企业代号']==id1]\n",
1910 |     "    all_num = tem.shape[0]\n",
1911 |     "    fei_num = tem[tem['发票状态']=='作废发票'].shape[0]\n",
1912 |     "    ratio = fei_num/all_num\n",
1913 |     "    \n",
1914 |     "    r_out.append(ratio)\n",
1915 |     "\n",
1916 |     "    \n",
1917 |     "\n",
1918 |     "name=[]    \n",
1919 |     "for num in range(1,303):\n",
1920 |     "    id1 = 'E'+str(num+123)\n",
1921 |     "    name.append(id1)\n",
1922 |     "    "
1923 |    ]
1924 |   },
1925 |   {
1926 |    "cell_type": "code",
1927 |    "execution_count": 8,
1928 |    "metadata": {},
1929 |    "outputs": [],
1930 |    "source": [
1931 |     "in_num=[]\n",
1932 |     "for num in range(1,303):\n",
1933 |     "    id1 = 'E'+str(num+123)\n",
1934 |     "    tem = input1[input1['企业代号']==id1]\n",
1935 |     "    all_num = tem.shape[0]\n",
1936 |     "    \n",
1937 |     "    in_num.append(all_num)\n",
1938 |     "    \n",
1939 |     "out_num=[]\n",
1940 |     "for num in range(1,303):\n",
1941 |     "    id1 = 'E'+str(num+123)\n",
1942 |     "    tem = output1[output1['企业代号']==id1]\n",
1943 |     "    all_num = tem.shape[0]\n",
1944 |     "    \n",
1945 |     "    out_num.append(all_num)"
1946 |    ]
1947 |   },
1948 |   {
1949 |    "cell_type": "code",
1950 |    "execution_count": 10,
1951 |    "metadata": {},
1952 |    "outputs": [
1953 |     {
1954 |      "data": {
1955 |       "text/html": [
1956 |        "<div>\n",
1957 |        "<style scoped>\n",
1958 |        "    .dataframe tbody tr th:only-of-type {\n",
1959 |        "        vertical-align: middle;\n",
1960 |        "    }\n",
1961 |        "\n",
1962 |        "    .dataframe tbody tr th {\n",
1963 |        "        vertical-align: top;\n",
1964 |        "    }\n",
1965 |        "\n",
1966 |        "    .dataframe thead th {\n",
1967 |        "        text-align: right;\n",
1968 |        "    }\n",
1969 |        "</style>\n",
1970 |        "<table border=\"1\" class=\"dataframe\">\n",
1971 |        "  <thead>\n",
1972 |        "    <tr style=\"text-align: right;\">\n",
1973 |        "      <th></th>\n",
1974 |        "      <th>企业名称</th>\n",
1975 |        "      <th>进项发票的作废比例</th>\n",
1976 |        "      <th>销项发票的作废比例</th>\n",
1977 |        "    </tr>\n",
1978 |        "  </thead>\n",
1979 |        "  <tbody>\n",
1980 |        "    <tr>\n",
1981 |        "      <th>0</th>\n",
1982 |        "      <td>E124</td>\n",
1983 |        "      <td>0.123313</td>\n",
1984 |        "      <td>0.150039</td>\n",
1985 |        "    </tr>\n",
1986 |        "    <tr>\n",
1987 |        "      <th>1</th>\n",
1988 |        "      <td>E125</td>\n",
1989 |        "      <td>0.123817</td>\n",
1990 |        "      <td>0.134796</td>\n",
1991 |        "    </tr>\n",
1992 |        "    <tr>\n",
1993 |        "      <th>2</th>\n",
1994 |        "      <td>E126</td>\n",
1995 |        "      <td>0.033771</td>\n",
1996 |        "      <td>0.166227</td>\n",
1997 |        "    </tr>\n",
1998 |        "    <tr>\n",
1999 |        "      <th>3</th>\n",
2000 |        "      <td>E127</td>\n",
2001 |        "      <td>0.017931</td>\n",
2002 |        "      <td>0.030303</td>\n",
2003 |        "    </tr>\n",
2004 |        "    <tr>\n",
2005 |        "      <th>4</th>\n",
2006 |        "      <td>E128</td>\n",
2007 |        "      <td>0.027312</td>\n",
2008 |        "      <td>0.074900</td>\n",
2009 |        "    </tr>\n",
2010 |        "    <tr>\n",
2011 |        "      <th>...</th>\n",
2012 |        "      <td>...</td>\n",
2013 |        "      <td>...</td>\n",
2014 |        "      <td>...</td>\n",
2015 |        "    </tr>\n",
2016 |        "    <tr>\n",
2017 |        "      <th>297</th>\n",
2018 |        "      <td>E421</td>\n",
2019 |        "      <td>0.000000</td>\n",
2020 |        "      <td>0.034483</td>\n",
2021 |        "    </tr>\n",
2022 |        "    <tr>\n",
2023 |        "      <th>298</th>\n",
2024 |        "      <td>E422</td>\n",
2025 |        "      <td>0.000000</td>\n",
2026 |        "      <td>0.100000</td>\n",
2027 |        "    </tr>\n",
2028 |        "    <tr>\n",
2029 |        "      <th>299</th>\n",
2030 |        "      <td>E423</td>\n",
2031 |        "      <td>0.000000</td>\n",
2032 |        "      <td>0.142857</td>\n",
2033 |        "    </tr>\n",
2034 |        "    <tr>\n",
2035 |        "      <th>300</th>\n",
2036 |        "      <td>E424</td>\n",
2037 |        "      <td>0.000000</td>\n",
2038 |        "      <td>0.139535</td>\n",
2039 |        "    </tr>\n",
2040 |        "    <tr>\n",
2041 |        "      <th>301</th>\n",
2042 |        "      <td>E425</td>\n",
2043 |        "      <td>0.016949</td>\n",
2044 |        "      <td>0.444444</td>\n",
2045 |        "    </tr>\n",
2046 |        "  </tbody>\n",
2047 |        "</table>\n",
2048 |        "<p>302 rows × 3 columns</p>\n",
2049 |        "</div>"
2050 |       ],
2051 |       "text/plain": [
2052 |        "     企业名称  进项发票的作废比例  销项发票的作废比例\n",
2053 |        "0    E124   0.123313   0.150039\n",
2054 |        "1    E125   0.123817   0.134796\n",
2055 |        "2    E126   0.033771   0.166227\n",
2056 |        "3    E127   0.017931   0.030303\n",
2057 |        "4    E128   0.027312   0.074900\n",
2058 |        "..    ...        ...        ...\n",
2059 |        "297  E421   0.000000   0.034483\n",
2060 |        "298  E422   0.000000   0.100000\n",
2061 |        "299  E423   0.000000   0.142857\n",
2062 |        "300  E424   0.000000   0.139535\n",
2063 |        "301  E425   0.016949   0.444444\n",
2064 |        "\n",
2065 |        "[302 rows x 3 columns]"
2066 |       ]
2067 |      },
2068 |      "execution_count": 10,
2069 |      "metadata": {},
2070 |      "output_type": "execute_result"
2071 |     }
2072 |    ],
2073 |    "source": [
2074 |     "data = {'企业名称':name,\n",
2075 |     "    '进项发票的作废比例':r_in   ,\n",
2076 |     "      '销项发票的作废比例':r_out  \n",
2077 |     "}\n",
2078 |     "\n",
2079 |     "df=pd.DataFrame(data=data)\n",
2080 |     "df"
2081 |    ]
2082 |   },
2083 |   {
2084 |    "cell_type": "code",
2085 |    "execution_count": 11,
2086 |    "metadata": {},
2087 |    "outputs": [],
2088 |    "source": [
2089 |     "df.to_csv('第二问作废比例.csv',encoding='gbk')"
2090 |    ]
2091 |   },
2092 |   {
2093 |    "cell_type": "code",
2094 |    "execution_count": 12,
2095 |    "metadata": {},
2096 |    "outputs": [],
2097 |    "source": [
2098 |     "new_in = input1[(input1['开票日期']<'2020')]    # 2020年之前的进项数据\n",
2099 |     "new_out = output1[(output1['开票日期']<'2020')]"
2100 |    ]
2101 |   },
2102 |   {
2103 |    "cell_type": "code",
2104 |    "execution_count": 13,
2105 |    "metadata": {},
2106 |    "outputs": [],
2107 |    "source": [
2108 |     "ur = []\n",
2109 |     "\n",
2110 |     "dd = []\n",
2111 |     "for num in range(1,303):      # 遍历目标企业\n",
2112 |     "    \n",
2113 |     "    id1 = 'E'+str(num+123)\n",
2114 |     "    a = new_in[new_in['企业代号']==id1]\n",
2115 |     "    a = a.reset_index(drop=True)\n",
2116 |     "    \n",
2117 |     "    end_1 = a['开票日期'][len(a)-1].year\n",
2118 |     "    begin_1 = a['开票日期'][0].year\n",
2119 |     "    \n",
2120 |     "    begin_ji_1 = a[(a['开票日期']>str(begin_1))&(a['开票日期']<str(begin_1+1))]['金额'].sum()\n",
2121 |     "    end_ji_1 =  a[(a['开票日期']>str(end_1))&(a['开票日期']<str(end_1+1))]['金额'].sum()\n",
2122 |     "    \n",
2123 |     "    \n",
2124 |     "    b = new_out[new_out['企业代号']==id1]\n",
2125 |     "    b = b.reset_index(drop=True)\n",
2126 |     "    \n",
2127 |     "    end_2 = b['开票日期'][len(b)-1].year\n",
2128 |     "    begin_2 = b['开票日期'][0].year\n",
2129 |     "    \n",
2130 |     "    begin_ji_2 = b[(b['开票日期']>str(begin_2))&(b['开票日期']<str(begin_2+1))]['金额'].sum()\n",
2131 |     "    end_ji_2 =  b[(b['开票日期']>str(end_2))&(b['开票日期']<str(end_2+1))]['金额'].sum()\n",
2132 |     "    \n",
2133 |     "    up_rate = (end_ji_2-end_ji_1)/(begin_ji_2-begin_ji_1)\n",
2134 |     "    \n",
2135 |     "    d = (end_ji_2-end_ji_1)-(begin_ji_2-begin_ji_1)\n",
2136 |     "    \n",
2137 |     "    \n",
2138 |     "    ur.append(up_rate)\n",
2139 |     "    dd.append(d)"
2140 |    ]
2141 |   },
2142 |   {
2143 |    "cell_type": "code",
2144 |    "execution_count": 14,
2145 |    "metadata": {},
2146 |    "outputs": [
2147 |     {
2148 |      "data": {
2149 |       "text/html": [
2150 |        "<div>\n",
2151 |        "<style scoped>\n",
2152 |        "    .dataframe tbody tr th:only-of-type {\n",
2153 |        "        vertical-align: middle;\n",
2154 |        "    }\n",
2155 |        "\n",
2156 |        "    .dataframe tbody tr th {\n",
2157 |        "        vertical-align: top;\n",
2158 |        "    }\n",
2159 |        "\n",
2160 |        "    .dataframe thead th {\n",
2161 |        "        text-align: right;\n",
2162 |        "    }\n",
2163 |        "</style>\n",
2164 |        "<table border=\"1\" class=\"dataframe\">\n",
2165 |        "  <thead>\n",
2166 |        "    <tr style=\"text-align: right;\">\n",
2167 |        "      <th></th>\n",
2168 |        "      <th>绝对数变化</th>\n",
2169 |        "      <th>比例变化</th>\n",
2170 |        "    </tr>\n",
2171 |        "  </thead>\n",
2172 |        "  <tbody>\n",
2173 |        "    <tr>\n",
2174 |        "      <th>0</th>\n",
2175 |        "      <td>-1.065813e+08</td>\n",
2176 |        "      <td>-2.086819</td>\n",
2177 |        "    </tr>\n",
2178 |        "    <tr>\n",
2179 |        "      <th>1</th>\n",
2180 |        "      <td>-1.697853e+08</td>\n",
2181 |        "      <td>-1.069323</td>\n",
2182 |        "    </tr>\n",
2183 |        "    <tr>\n",
2184 |        "      <th>2</th>\n",
2185 |        "      <td>1.540513e+08</td>\n",
2186 |        "      <td>2.527125</td>\n",
2187 |        "    </tr>\n",
2188 |        "    <tr>\n",
2189 |        "      <th>3</th>\n",
2190 |        "      <td>-8.365728e+07</td>\n",
2191 |        "      <td>0.677000</td>\n",
2192 |        "    </tr>\n",
2193 |        "    <tr>\n",
2194 |        "      <th>4</th>\n",
2195 |        "      <td>8.388073e+07</td>\n",
2196 |        "      <td>2.918189</td>\n",
2197 |        "    </tr>\n",
2198 |        "    <tr>\n",
2199 |        "      <th>...</th>\n",
2200 |        "      <td>...</td>\n",
2201 |        "      <td>...</td>\n",
2202 |        "    </tr>\n",
2203 |        "    <tr>\n",
2204 |        "      <th>297</th>\n",
2205 |        "      <td>-5.554860e+04</td>\n",
2206 |        "      <td>0.110407</td>\n",
2207 |        "    </tr>\n",
2208 |        "    <tr>\n",
2209 |        "      <th>298</th>\n",
2210 |        "      <td>1.892226e+04</td>\n",
2211 |        "      <td>6.340986</td>\n",
2212 |        "    </tr>\n",
2213 |        "    <tr>\n",
2214 |        "      <th>299</th>\n",
2215 |        "      <td>1.143155e+04</td>\n",
2216 |        "      <td>0.214670</td>\n",
2217 |        "    </tr>\n",
2218 |        "    <tr>\n",
2219 |        "      <th>300</th>\n",
2220 |        "      <td>-8.175862e+04</td>\n",
2221 |        "      <td>2.007337</td>\n",
2222 |        "    </tr>\n",
2223 |        "    <tr>\n",
2224 |        "      <th>301</th>\n",
2225 |        "      <td>-1.218773e+05</td>\n",
2226 |        "      <td>-0.132198</td>\n",
2227 |        "    </tr>\n",
2228 |        "  </tbody>\n",
2229 |        "</table>\n",
2230 |        "<p>302 rows × 2 columns</p>\n",
2231 |        "</div>"
2232 |       ],
2233 |       "text/plain": [
2234 |        "            绝对数变化      比例变化\n",
2235 |        "0   -1.065813e+08 -2.086819\n",
2236 |        "1   -1.697853e+08 -1.069323\n",
2237 |        "2    1.540513e+08  2.527125\n",
2238 |        "3   -8.365728e+07  0.677000\n",
2239 |        "4    8.388073e+07  2.918189\n",
2240 |        "..            ...       ...\n",
2241 |        "297 -5.554860e+04  0.110407\n",
2242 |        "298  1.892226e+04  6.340986\n",
2243 |        "299  1.143155e+04  0.214670\n",
2244 |        "300 -8.175862e+04  2.007337\n",
2245 |        "301 -1.218773e+05 -0.132198\n",
2246 |        "\n",
2247 |        "[302 rows x 2 columns]"
2248 |       ]
2249 |      },
2250 |      "execution_count": 14,
2251 |      "metadata": {},
2252 |      "output_type": "execute_result"
2253 |     }
2254 |    ],
2255 |    "source": [
2256 |     "data3 = {'绝对数变化':dd,\n",
2257 |     "        '比例变化':ur}\n",
2258 |     "df3 = pd.DataFrame(data=data3)\n",
2259 |     "df3"
2260 |    ]
2261 |   },
2262 |   {
2263 |    "cell_type": "code",
2264 |    "execution_count": 15,
2265 |    "metadata": {},
2266 |    "outputs": [
2267 |     {
2268 |      "data": {
2269 |       "text/html": [
2270 |        "<div>\n",
2271 |        "<style scoped>\n",
2272 |        "    .dataframe tbody tr th:only-of-type {\n",
2273 |        "        vertical-align: middle;\n",
2274 |        "    }\n",
2275 |        "\n",
2276 |        "    .dataframe tbody tr th {\n",
2277 |        "        vertical-align: top;\n",
2278 |        "    }\n",
2279 |        "\n",
2280 |        "    .dataframe thead th {\n",
2281 |        "        text-align: right;\n",
2282 |        "    }\n",
2283 |        "</style>\n",
2284 |        "<table border=\"1\" class=\"dataframe\">\n",
2285 |        "  <thead>\n",
2286 |        "    <tr style=\"text-align: right;\">\n",
2287 |        "      <th></th>\n",
2288 |        "      <th>绝对数变化</th>\n",
2289 |        "      <th>比例变化</th>\n",
2290 |        "      <th>是否扭亏为盈利</th>\n",
2291 |        "      <th>是否变为亏损</th>\n",
2292 |        "    </tr>\n",
2293 |        "  </thead>\n",
2294 |        "  <tbody>\n",
2295 |        "    <tr>\n",
2296 |        "      <th>0</th>\n",
2297 |        "      <td>-1.065813e+08</td>\n",
2298 |        "      <td>-2.086819</td>\n",
2299 |        "      <td>0.0</td>\n",
2300 |        "      <td>1.0</td>\n",
2301 |        "    </tr>\n",
2302 |        "    <tr>\n",
2303 |        "      <th>1</th>\n",
2304 |        "      <td>-1.697853e+08</td>\n",
2305 |        "      <td>-1.069323</td>\n",
2306 |        "      <td>0.0</td>\n",
2307 |        "      <td>1.0</td>\n",
2308 |        "    </tr>\n",
2309 |        "    <tr>\n",
2310 |        "      <th>2</th>\n",
2311 |        "      <td>1.540513e+08</td>\n",
2312 |        "      <td>2.527125</td>\n",
2313 |        "      <td>0.0</td>\n",
2314 |        "      <td>0.0</td>\n",
2315 |        "    </tr>\n",
2316 |        "    <tr>\n",
2317 |        "      <th>3</th>\n",
2318 |        "      <td>-8.365728e+07</td>\n",
2319 |        "      <td>0.677000</td>\n",
2320 |        "      <td>0.0</td>\n",
2321 |        "      <td>0.0</td>\n",
2322 |        "    </tr>\n",
2323 |        "    <tr>\n",
2324 |        "      <th>4</th>\n",
2325 |        "      <td>8.388073e+07</td>\n",
2326 |        "      <td>2.918189</td>\n",
2327 |        "      <td>0.0</td>\n",
2328 |        "      <td>0.0</td>\n",
2329 |        "    </tr>\n",
2330 |        "    <tr>\n",
2331 |        "      <th>...</th>\n",
2332 |        "      <td>...</td>\n",
2333 |        "      <td>...</td>\n",
2334 |        "      <td>...</td>\n",
2335 |        "      <td>...</td>\n",
2336 |        "    </tr>\n",
2337 |        "    <tr>\n",
2338 |        "      <th>297</th>\n",
2339 |        "      <td>-5.554860e+04</td>\n",
2340 |        "      <td>0.110407</td>\n",
2341 |        "      <td>0.0</td>\n",
2342 |        "      <td>0.0</td>\n",
2343 |        "    </tr>\n",
2344 |        "    <tr>\n",
2345 |        "      <th>298</th>\n",
2346 |        "      <td>1.892226e+04</td>\n",
2347 |        "      <td>6.340986</td>\n",
2348 |        "      <td>0.0</td>\n",
2349 |        "      <td>0.0</td>\n",
2350 |        "    </tr>\n",
2351 |        "    <tr>\n",
2352 |        "      <th>299</th>\n",
2353 |        "      <td>1.143155e+04</td>\n",
2354 |        "      <td>0.214670</td>\n",
2355 |        "      <td>0.0</td>\n",
2356 |        "      <td>0.0</td>\n",
2357 |        "    </tr>\n",
2358 |        "    <tr>\n",
2359 |        "      <th>300</th>\n",
2360 |        "      <td>-8.175862e+04</td>\n",
2361 |        "      <td>2.007337</td>\n",
2362 |        "      <td>0.0</td>\n",
2363 |        "      <td>0.0</td>\n",
2364 |        "    </tr>\n",
2365 |        "    <tr>\n",
2366 |        "      <th>301</th>\n",
2367 |        "      <td>-1.218773e+05</td>\n",
2368 |        "      <td>-0.132198</td>\n",
2369 |        "      <td>0.0</td>\n",
2370 |        "      <td>1.0</td>\n",
2371 |        "    </tr>\n",
2372 |        "  </tbody>\n",
2373 |        "</table>\n",
2374 |        "<p>302 rows × 4 columns</p>\n",
2375 |        "</div>"
2376 |       ],
2377 |       "text/plain": [
2378 |        "            绝对数变化      比例变化  是否扭亏为盈利  是否变为亏损\n",
2379 |        "0   -1.065813e+08 -2.086819      0.0     1.0\n",
2380 |        "1   -1.697853e+08 -1.069323      0.0     1.0\n",
2381 |        "2    1.540513e+08  2.527125      0.0     0.0\n",
2382 |        "3   -8.365728e+07  0.677000      0.0     0.0\n",
2383 |        "4    8.388073e+07  2.918189      0.0     0.0\n",
2384 |        "..            ...       ...      ...     ...\n",
2385 |        "297 -5.554860e+04  0.110407      0.0     0.0\n",
2386 |        "298  1.892226e+04  6.340986      0.0     0.0\n",
2387 |        "299  1.143155e+04  0.214670      0.0     0.0\n",
2388 |        "300 -8.175862e+04  2.007337      0.0     0.0\n",
2389 |        "301 -1.218773e+05 -0.132198      0.0     1.0\n",
2390 |        "\n",
2391 |        "[302 rows x 4 columns]"
2392 |       ]
2393 |      },
2394 |      "execution_count": 15,
2395 |      "metadata": {},
2396 |      "output_type": "execute_result"
2397 |     }
2398 |    ],
2399 |    "source": [
2400 |     "for i in range(len(df3)):\n",
2401 |     "    if (df3.loc[i,'绝对数变化']>0) & (df3.loc[i,'比例变化']<0):     # 说明扭亏为盈\n",
2402 |     "        df3.loc[i,'是否扭亏为盈利']=1\n",
2403 |     "    else:\n",
2404 |     "        df3.loc[i,'是否扭亏为盈利']=0\n",
2405 |     "\n",
2406 |     "for i in range(len(df3)):\n",
2407 |     "    if (df3.loc[i,'绝对数变化']<0) & (df3.loc[i,'比例变化']<0):     # 说明扭亏为盈\n",
2408 |     "        df3.loc[i,'是否变为亏损']=1\n",
2409 |     "    else:\n",
2410 |     "        df3.loc[i,'是否变为亏损']=0        \n",
2411 |     "\n",
2412 |     "df3"
2413 |    ]
2414 |   },
2415 |   {
2416 |    "cell_type": "code",
2417 |    "execution_count": 16,
2418 |    "metadata": {},
2419 |    "outputs": [],
2420 |    "source": [
2421 |     "df3.to_csv('第二问绝对数和比例变化.csv',encoding='gbk')"
2422 |    ]
2423 |   },
2424 |   {
2425 |    "cell_type": "code",
2426 |    "execution_count": null,
2427 |    "metadata": {},
2428 |    "outputs": [],
2429 |    "source": []
2430 |   }
2431 |  ],
2432 |  "metadata": {
2433 |   "kernelspec": {
2434 |    "display_name": "Python [conda env:root] *",
2435 |    "language": "python",
2436 |    "name": "conda-root-py"
2437 |   },
2438 |   "language_info": {
2439 |    "codemirror_mode": {
2440 |     "name": "ipython",
2441 |     "version": 3
2442 |    },
2443 |    "file_extension": ".py",
2444 |    "mimetype": "text/x-python",
2445 |    "name": "python",
2446 |    "nbconvert_exporter": "python",
2447 |    "pygments_lexer": "ipython3",
2448 |    "version": "3.7.6"
2449 |   },
2450 |   "toc": {
2451 |    "base_numbering": 1,
2452 |    "nav_menu": {},
2453 |    "number_sections": true,
2454 |    "sideBar": true,
2455 |    "skip_h1_title": false,
2456 |    "title_cell": "Table of Contents",
2457 |    "title_sidebar": "Contents",
2458 |    "toc_cell": false,
2459 |    "toc_position": {},
2460 |    "toc_section_display": true,
2461 |    "toc_window_display": false
2462 |   }
2463 |  },
2464 |  "nbformat": 4,
2465 |  "nbformat_minor": 4
2466 | }
2467 | 


--------------------------------------------------------------------------------
/论文.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/leek-emperor/2020-CMCM-C/1d8a26c3a095726d45e107581c4bb204992b6e28/论文.pdf


--------------------------------------------------------------------------------