Initial commit

src/test.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 170,
    "metadata": {
     "collapsed": true,
     "pycharm": {
@@ -15,7 +15,7 @@
     "import pandas as pd\n",
     "from sklearn.model_selection import train_test_split\n",
     "from sklift.datasets import fetch_hillstrom\n",
-    "from sklift.metrics import uplift_at_k\n",
+    "from sklift.metrics import uplift_at_k, uplift_by_percentile, weighted_average_uplift\n",
     "from sklift.viz import plot_uplift_preds\n",
     "from sklift.models import SoloModel\n",
     "from catboost import CatBoostClassifier\n",
@@ -24,32 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "{'new_filter': 'filter'}"
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "filters = {}\n",
-    "filters['new_filter'] = 'filter'\n",
-    "filters"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 115,
+   "execution_count": 157,
    "outputs": [],
    "source": [
     "def get_data() -> tuple[Any, Any, Any]:\n",
@@ -75,54 +50,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 116,
+   "execution_count": 171,
    "outputs": [],
    "source": [
-    "data, target, treatment = get_data()"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 117,
-   "outputs": [],
-   "source": [
-    "X_train, X_val, y_train, y_val, trmnt_train, trmnt_val = train_test_split(\n",
-    "    data, target, treatment, test_size=0.5, random_state=42\n",
-    ")\n",
-    "\n",
-    "models_results = {\n",
-    "    'approach': [],\n",
-    "    'uplift@30%': []\n",
-    "}"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 118,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "0    0.871545\n1    0.128455\nName: visit, dtype: float64"
-     },
-     "execution_count": 118,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "y_train.value_counts(normalize=True)"
+    "data, target, treatment = get_data()\n",
+    "uplift = [1 for _ in data.index]"
    ],
    "metadata": {
     "collapsed": false,
@@ -133,19 +65,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 119,
+   "execution_count": 172,
    "outputs": [
     {
      "data": {
-      "text/plain": "0    0.870802\n1    0.129198\nName: visit, dtype: float64"
+      "text/plain": "0.04515395574087702"
      },
-     "execution_count": 119,
+     "execution_count": 172,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "y_val.value_counts(normalize=True)"
+    "weighted_average_uplift(target, uplift, treatment)"
    ],
    "metadata": {
     "collapsed": false,
@@ -156,44 +88,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "       recency   history_segment  history  mens  womens   zip_code  newbie  \\\n609          9    3) $200 - $350   212.32     1       0  Surburban       0   \n51952        3  6) $750 - $1,000   849.16     1       1  Surburban       1   \n33629        9      1) $0 - $100    43.22     1       0  Surburban       1   \n22103        8      1) $0 - $100    29.99     0       1  Surburban       0   \n21350        7    2) $100 - $200   164.07     1       0  Surburban       1   \n...        ...               ...      ...   ...     ...        ...     ...   \n9307         1    2) $100 - $200   110.45     0       1      Urban       0   \n16819        1      1) $0 - $100    88.04     0       1  Surburban       0   \n57173        1      1) $0 - $100    72.63     0       1      Rural       0   \n1282         3    4) $350 - $500   366.16     0       1      Rural       0   \n23624        9      1) $0 - $100    36.87     1       0      Urban       1   \n\n            channel  \n609    Multichannel  \n51952  Multichannel  \n33629         Phone  \n22103           Web  \n21350         Phone  \n...             ...  \n9307          Phone  \n16819         Phone  \n57173         Phone  \n1282          Phone  \n23624           Web  \n\n[29885 rows x 8 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>recency</th>\n      <th>history_segment</th>\n      <th>history</th>\n      <th>mens</th>\n      <th>womens</th>\n      <th>zip_code</th>\n      <th>newbie</th>\n      <th>channel</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>609</th>\n      <td>9</td>\n      <td>3) $200 - $350</td>\n      <td>212.32</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Surburban</td>\n      <td>0</td>\n      <td>Multichannel</td>\n    </tr>\n    <tr>\n      <th>51952</th>\n      <td>3</td>\n      <td>6) $750 - $1,000</td>\n      <td>849.16</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Multichannel</td>\n    </tr>\n    <tr>\n      <th>33629</th>\n      <td>9</td>\n      <td>1) $0 - $100</td>\n      <td>43.22</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>22103</th>\n      <td>8</td>\n      <td>1) $0 - $100</td>\n      <td>29.99</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Surburban</td>\n      <td>0</td>\n      <td>Web</td>\n    </tr>\n    <tr>\n      <th>21350</th>\n      <td>7</td>\n      <td>2) $100 - $200</td>\n      <td>164.07</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>9307</th>\n      <td>1</td>\n      <td>2) $100 - $200</td>\n      <td>110.45</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Urban</td>\n      <td>0</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>16819</th>\n      <td>1</td>\n      <td>1) $0 - $100</td>\n      <td>88.04</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Surburban</td>\n      <td>0</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>57173</th>\n      <td>1</td>\n      <td>1) $0 - $100</td>\n      <td>72.63</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Rural</td>\n      <td>0</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>1282</th>\n      <td>3</td>\n      <td>4) $350 - $500</td>\n      <td>366.16</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Rural</td>\n      <td>0</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>23624</th>\n      <td>9</td>\n      <td>1) $0 - $100</td>\n      <td>36.87</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Urban</td>\n      <td>1</td>\n      <td>Web</td>\n    </tr>\n  </tbody>\n</table>\n<p>29885 rows × 8 columns</p>\n</div>"
-     },
-     "execution_count": 113,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "X_train"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 114,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "       recency history_segment  history  mens  womens   zip_code  newbie  \\\n7730         3  5) $500 - $750   503.73     0       1      Rural       1   \n17594        5  2) $100 - $200   163.39     1       0      Urban       0   \n14481       11  3) $200 - $350   287.77     1       0      Rural       1   \n20003        3    1) $0 - $100    29.99     0       1  Surburban       1   \n19981        5  2) $100 - $200   131.51     0       1      Urban       1   \n...        ...             ...      ...   ...     ...        ...     ...   \n41828       11  4) $350 - $500   457.09     0       1  Surburban       1   \n49354        2    1) $0 - $100    29.99     0       1      Rural       1   \n12063        9  2) $100 - $200   147.48     1       0      Rural       1   \n3757        10  2) $100 - $200   128.78     1       0  Surburban       1   \n10708        6  2) $100 - $200   138.72     1       0      Urban       0   \n\n            channel  \n7730   Multichannel  \n17594           Web  \n14481           Web  \n20003           Web  \n19981           Web  \n...             ...  \n41828  Multichannel  \n49354         Phone  \n12063         Phone  \n3757          Phone  \n10708           Web  \n\n[12808 rows x 8 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>recency</th>\n      <th>history_segment</th>\n      <th>history</th>\n      <th>mens</th>\n      <th>womens</th>\n      <th>zip_code</th>\n      <th>newbie</th>\n      <th>channel</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>7730</th>\n      <td>3</td>\n      <td>5) $500 - $750</td>\n      <td>503.73</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Rural</td>\n      <td>1</td>\n      <td>Multichannel</td>\n    </tr>\n    <tr>\n      <th>17594</th>\n      <td>5</td>\n      <td>2) $100 - $200</td>\n      <td>163.39</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Urban</td>\n      <td>0</td>\n      <td>Web</td>\n    </tr>\n    <tr>\n      <th>14481</th>\n      <td>11</td>\n      <td>3) $200 - $350</td>\n      <td>287.77</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Rural</td>\n      <td>1</td>\n      <td>Web</td>\n    </tr>\n    <tr>\n      <th>20003</th>\n      <td>3</td>\n      <td>1) $0 - $100</td>\n      <td>29.99</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Web</td>\n    </tr>\n    <tr>\n      <th>19981</th>\n      <td>5</td>\n      <td>2) $100 - $200</td>\n      <td>131.51</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Urban</td>\n      <td>1</td>\n      <td>Web</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>41828</th>\n      <td>11</td>\n      <td>4) $350 - $500</td>\n      <td>457.09</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Multichannel</td>\n    </tr>\n    <tr>\n      <th>49354</th>\n      <td>2</td>\n      <td>1) $0 - $100</td>\n      <td>29.99</td>\n      <td>0</td>\n      <td>1</td>\n      <td>Rural</td>\n      <td>1</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>12063</th>\n      <td>9</td>\n      <td>2) $100 - $200</td>\n      <td>147.48</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Rural</td>\n      <td>1</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>3757</th>\n      <td>10</td>\n      <td>2) $100 - $200</td>\n      <td>128.78</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Surburban</td>\n      <td>1</td>\n      <td>Phone</td>\n    </tr>\n    <tr>\n      <th>10708</th>\n      <td>6</td>\n      <td>2) $100 - $200</td>\n      <td>138.72</td>\n      <td>1</td>\n      <td>0</td>\n      <td>Urban</td>\n      <td>0</td>\n      <td>Web</td>\n    </tr>\n  </tbody>\n</table>\n<p>12808 rows × 8 columns</p>\n</div>"
-     },
-     "execution_count": 114,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "execution_count": 159,
+   "outputs": [],
    "source": [
-    "X_val"
+    "X_train, X_val, y_train, y_val, trmnt_train, trmnt_val = train_test_split(\n",
+    "    data, target, treatment, test_size=0.5, random_state=42\n",
+    ")\n",
+    "\n",
+    "models_results = {\n",
+    "    'approach': [],\n",
+    "    'uplift@30%': []\n",
+    "}"
    ],
    "metadata": {
     "collapsed": false,
@@ -204,13 +109,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 139,
+   "execution_count": 162,
    "outputs": [],
    "source": [
-    "t = pd.DataFrame(data = [1 for _ in X_train.index],\n",
-    "    index=X_train.index\n",
-    ")\n",
-    "# t.loc[t.index] = 10"
+    "new_val = X_val.loc[X_val[X_val['newbie'] == 1].index]\n",
+    "new_y = y_val.loc[new_val.index]\n",
+    "new_trmt = trmnt_val.loc[new_val.index]\n",
+    "uplift = [np.random.random() for _ in new_val.index]"
    ],
    "metadata": {
     "collapsed": false,
@@ -221,20 +126,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 140,
+   "execution_count": 163,
    "outputs": [
     {
      "data": {
-      "text/plain": "       0\n15194  1\n23642  1\n57737  1\n33880  1\n21211  1\n...   ..\n9307   1\n16819  1\n57173  1\n1282   1\n23624  1\n\n[21346 rows x 1 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>0</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>15194</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>23642</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>57737</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>33880</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>21211</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>9307</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>16819</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>57173</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1282</th>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>23624</th>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>21346 rows × 1 columns</p>\n</div>"
+      "text/plain": "0.07056871131907891"
      },
-     "execution_count": 140,
+     "execution_count": 163,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "t"
+    "uplift_at_k(y_true=new_y, uplift=uplift, treatment=new_trmt, strategy='by_group', k=0.3)"
    ],
    "metadata": {
     "collapsed": false,
@@ -245,20 +149,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 152,
+   "execution_count": 165,
    "outputs": [
     {
      "data": {
-      "text/plain": "0.1987362209568153"
+      "text/plain": "            n_treatment  n_control  response_rate_treatment  \\\npercentile                                                    \n0-10                549        515                 0.149362   \n10-20               553        511                 0.113924   \n20-30               511        553                 0.138943   \n30-40               546        518                 0.130037   \n40-50               544        520                 0.156250   \n50-60               542        521                 0.153137   \n60-70               518        545                 0.106178   \n70-80               529        534                 0.130435   \n80-90               528        535                 0.128788   \n90-100              539        524                 0.116883   \n\n            response_rate_control    uplift  \npercentile                                   \n0-10                     0.054369  0.094994  \n10-20                    0.066536  0.047388  \n20-30                    0.070524  0.068419  \n30-40                    0.090734  0.039303  \n40-50                    0.080769  0.075481  \n50-60                    0.078695  0.074442  \n60-70                    0.056881  0.049297  \n70-80                    0.071161  0.059274  \n80-90                    0.069159  0.059629  \n90-100                   0.085878  0.031005  ",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>n_treatment</th>\n      <th>n_control</th>\n      <th>response_rate_treatment</th>\n      <th>response_rate_control</th>\n      <th>uplift</th>\n    </tr>\n    <tr>\n      <th>percentile</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0-10</th>\n      <td>549</td>\n      <td>515</td>\n      <td>0.149362</td>\n      <td>0.054369</td>\n      <td>0.094994</td>\n    </tr>\n    <tr>\n      <th>10-20</th>\n      <td>553</td>\n      <td>511</td>\n      <td>0.113924</td>\n      <td>0.066536</td>\n      <td>0.047388</td>\n    </tr>\n    <tr>\n      <th>20-30</th>\n      <td>511</td>\n      <td>553</td>\n      <td>0.138943</td>\n      <td>0.070524</td>\n      <td>0.068419</td>\n    </tr>\n    <tr>\n      <th>30-40</th>\n      <td>546</td>\n      <td>518</td>\n      <td>0.130037</td>\n      <td>0.090734</td>\n      <td>0.039303</td>\n    </tr>\n    <tr>\n      <th>40-50</th>\n      <td>544</td>\n      <td>520</td>\n      <td>0.156250</td>\n      <td>0.080769</td>\n      <td>0.075481</td>\n    </tr>\n    <tr>\n      <th>50-60</th>\n      <td>542</td>\n      <td>521</td>\n      <td>0.153137</td>\n      <td>0.078695</td>\n      <td>0.074442</td>\n    </tr>\n    <tr>\n      <th>60-70</th>\n      <td>518</td>\n      <td>545</td>\n      <td>0.106178</td>\n      <td>0.056881</td>\n      <td>0.049297</td>\n    </tr>\n    <tr>\n      <th>70-80</th>\n      <td>529</td>\n      <td>534</td>\n      <td>0.130435</td>\n      <td>0.071161</td>\n      <td>0.059274</td>\n    </tr>\n    <tr>\n      <th>80-90</th>\n      <td>528</td>\n      <td>535</td>\n      <td>0.128788</td>\n      <td>0.069159</td>\n      <td>0.059629</td>\n    </tr>\n    <tr>\n      <th>90-100</th>\n      <td>539</td>\n      <td>524</td>\n      <td>0.116883</td>\n      <td>0.085878</td>\n      <td>0.031005</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
      },
-     "execution_count": 152,
+     "execution_count": 165,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "import numpy as np\n",
-    "np.random.random()"
+    "uplift_by_percentile(new_y, uplift, new_trmt)"
    ],
    "metadata": {
     "collapsed": false,
@@ -320,98 +224,6 @@
     }
    }
   },
-  {
-   "cell_type": "code",
-   "execution_count": 154,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "7730     0\n17594    0\n14481    0\n20003    0\n19981    0\n        ..\n20159    0\n54905    0\n22035    0\n32253    1\n18362    0\nName: visit, Length: 21347, dtype: int64"
-     },
-     "execution_count": 154,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "y_val"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 155,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "7730     0\n17594    1\n14481    1\n20003    1\n19981    0\n        ..\n20159    1\n54905    0\n22035    0\n32253    1\n18362    0\nName: segment, Length: 21347, dtype: int64"
-     },
-     "execution_count": 155,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "trmnt_val"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 153,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "0.07205126328781693"
-     },
-     "execution_count": 153,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "sm_score"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 121,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "array([ 0.03210443,  0.02052168, -0.00873204, ...,  0.04017716,\n        0.03415103,  0.04917549])"
-     },
-     "execution_count": 121,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "uplift_sm"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
   {
    "cell_type": "code",
    "execution_count": 14,

src/tools.py

@@ -141,8 +141,7 @@ def uplift_by_percentile():
 
 
 def get_weighted_average_uplift(target_test: pd.DataFrame, uplift, treatment_test: pd.DataFrame):
-	res = weighted_average_uplift(target_test, uplift, treatment_test)
-	return res
+	return weighted_average_uplift(target_test, uplift, treatment_test)
 
 
 def get_newbie_plot(data):

src/web_app.py

@@ -157,13 +157,12 @@ elif not surburban and not urban and not rural:
 
 if not disabled:
 	filtered_dataset = tools.filter_data(data_test, filters)
+	if filtered_dataset is None:
+		st.error('Не найдено пользователей для данных фильтров. Попробуйте изменить фильтры.')
 	# значение uplift для записей тех клиентов, который выбрал пользователь равен 1
 	import numpy as np
-	uplift = pd.DataFrame(
-		data=[np.random.random() for _ in filtered_dataset.index],
-		index=filtered_dataset.index
-		)
-	target_filtered =target_test.loc[filtered_dataset.index]
+	uplift = [1 for _ in filtered_dataset.index]
+	target_filtered = target_test.loc[filtered_dataset.index]
 	treatment_filtered = treatment_test.loc[filtered_dataset.index]
 	sample_size = 7 if filtered_dataset.shape[0] >= 7 else filtered_dataset.shape[0]
 	example = filtered_dataset.sample(sample_size)
@@ -174,11 +173,8 @@ if not disabled:
 
 send_promo = st.button('Отправить рекламу и посмотреть результат', disabled=disabled)
 if send_promo:
-	from sklift.metrics import uplift_by_percentile, uplift_at_k
-	st.write(uplift_by_percentile(y_true=target_filtered, uplift=uplift, treatment=treatment_filtered))
-	st.write(uplift_at_k(y_true=target_filtered, uplift=uplift, treatment=treatment_filtered, strategy='by_group', k=0.3))
+	st.write(tools.get_weighted_average_uplift(target_filtered, uplift, treatment_filtered))
 	# st.write(tools.get_weighted_average_uplift(target_filtered, uplift, treatment_filtered))
 
 # st.write('Если известно, на какой процент пользователей необходимо воздействовать, укажите это ниже')
 # st.slider(label='Процент пользователей', min_value=0, max_value=100, value=100)
-