{
"cells": [
{
"cell_type": "markdown",
"id": "9806d9ba",
"metadata": {},
"source": [
"# Перегрузка контактами снижает CTR\n",
"\n",
"**Вопрос:** падает ли CTR/CR при росте средней плотности показов на контактный день?\n",
"\n",
"**Гипотеза:** высокая плотность показов (спам) уменьшает CTR и вероятность заказа. Проверяем через ML-классификацию высокого CTR."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0891ca2a",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-12T19:11:23.062332Z",
"iopub.status.busy": "2025-12-12T19:11:23.062008Z",
"iopub.status.idle": "2025-12-12T19:11:29.703049Z",
"shell.execute_reply": "2025-12-12T19:11:29.700852Z"
}
},
"outputs": [],
"source": [
"import sqlite3\n",
"from pathlib import Path\n",
"import sys\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import roc_auc_score\n",
"\n",
"sns.set_theme(style=\"whitegrid\")\n",
"plt.rcParams[\"figure.figsize\"] = (10, 5)\n",
"\n",
"project_root = Path.cwd().resolve()\n",
"while not (project_root / \"preanalysis\").exists() and project_root.parent != project_root:\n",
" project_root = project_root.parent\n",
" project_root = project_root.parent\n",
"sys.path.append(str(project_root / \"preanalysis\"))\n",
"import eda_utils as eda\n",
"\n",
"db_path = project_root / \"dataset\" / \"ds.sqlite\"\n",
"conn = sqlite3.connect(db_path)\n",
"df = pd.read_sql_query(\"select * from communications\", conn, parse_dates=[\"business_dt\"])\n",
"conn.close()\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9f0e5ca7",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-12T19:11:29.710292Z",
"iopub.status.busy": "2025-12-12T19:11:29.709769Z",
"iopub.status.idle": "2025-12-12T19:11:32.169479Z",
"shell.execute_reply": "2025-12-12T19:11:32.167853Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" imp_total | \n",
" click_total | \n",
" orders_amt_total | \n",
" contact_days | \n",
" age | \n",
" gender_cd | \n",
" device_platform_cd | \n",
" ctr_all | \n",
" cr_click2order | \n",
" avg_imp_per_day | \n",
"
\n",
" \n",
" | id | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | 1 | \n",
" 68.0 | \n",
" 17.0 | \n",
" 0 | \n",
" 13 | \n",
" 58.0 | \n",
" M | \n",
" Android | \n",
" 0.250000 | \n",
" 0.000000 | \n",
" 5.230769 | \n",
"
\n",
" \n",
" | 2 | \n",
" 116.0 | \n",
" 23.0 | \n",
" 3 | \n",
" 15 | \n",
" 54.0 | \n",
" M | \n",
" Android | \n",
" 0.198276 | \n",
" 0.130435 | \n",
" 7.733333 | \n",
"
\n",
" \n",
" | 3 | \n",
" 293.0 | \n",
" 37.0 | \n",
" 2 | \n",
" 31 | \n",
" 70.0 | \n",
" F | \n",
" Android | \n",
" 0.126280 | \n",
" 0.054054 | \n",
" 9.451613 | \n",
"
\n",
" \n",
" | 4 | \n",
" 57.0 | \n",
" 15.0 | \n",
" 0 | \n",
" 12 | \n",
" 43.0 | \n",
" F | \n",
" Android | \n",
" 0.263158 | \n",
" 0.000000 | \n",
" 4.750000 | \n",
"
\n",
" \n",
" | 5 | \n",
" 43.0 | \n",
" 16.0 | \n",
" 1 | \n",
" 10 | \n",
" 46.0 | \n",
" M | \n",
" Android | \n",
" 0.372093 | \n",
" 0.062500 | \n",
" 4.300000 | \n",
"
\n",
" \n",
"
\n",
"