{ "cells": [ { "cell_type": "markdown", "id": "84dcd475", "metadata": {}, "source": [ "# DDRA - 001 - Basic Booking Attributes\n", "\n", "## General Idea\n", "The idea is to start with a very simple model with basic Booking attributes. This should serve as a first understanding of what can bring value in the data-driven risk assessment of new dash protected bookings.\n", "\n", "## Initial setup\n", "This first section just ensures that the connection to DWH works correctly." ] }, { "cell_type": "code", "execution_count": 1, "id": "12368ce1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "🔌 Testing connection using credentials at: /home/uri/.superhog-dwh/credentials.yml\n", "✅ Connection successful.\n" ] } ], "source": [ "# This script connects to a Data Warehouse (DWH) using PostgreSQL. \n", "# This should be common for all Notebooks, but you might need to adjust the path to the `dwh_utils` module.\n", "\n", "import sys\n", "import os\n", "sys.path.append(os.path.abspath(\"../../utils\")) # Adjust path if needed\n", "\n", "from dwh_utils import read_credentials, create_postgres_engine, query_to_dataframe, test_connection\n", "\n", "# --- Connect to DWH ---\n", "creds = read_credentials()\n", "dwh_pg_engine = create_postgres_engine(creds)\n", "\n", "# --- Test Query ---\n", "test_connection()" ] }, { "cell_type": "markdown", "id": "c86f94f1", "metadata": {}, "source": [ "## Data Extraction\n", "In this section we extract the data for our first attempt on Basic Booking Attributes modelling.\n", "\n", "This SQL query retrieves a clean and relevant subset of booking data for our model. It includes:\n", "- A **unique booking ID**\n", "- Key **numeric features** such as number of services, time between booking creation and check-in, and number of nights\n", "- Several **categorical (boolean) features** related to service usage\n", "- A **target variable** (`has_resolution_incident`) indicating whether a resolution incident occurred\n", "\n", "Filters applied being:\n", "1. Bookings from **\"New Dash\" users** with a valid deal ID\n", "2. Only **protected bookings**, i.e., those with Protection or Deposit Management services\n", "3. Bookings flagged for **risk categorisation** (excluding incomplete/rejected ones)\n", "4. Bookings that are **already completed**\n", "\n", "The result is converted into a pandas DataFrame for further processing and modeling.\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "3e3ed391", "metadata": {}, "outputs": [], "source": [ "# Initialise all imports needed for the Notebook\n", "from sklearn.model_selection import (\n", " train_test_split, \n", " GridSearchCV\n", ")\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.pipeline import Pipeline\n", "from sklearn.preprocessing import StandardScaler\n", "import pandas as pd\n", "import numpy as np\n", "from datetime import date\n", "from sklearn.metrics import (\n", " roc_auc_score, \n", " average_precision_score,\n", " classification_report,\n", " roc_curve, \n", " auc,\n", " precision_recall_curve\n", ")\n", "import matplotlib.pyplot as plt\n", "import shap" ] }, { "cell_type": "code", "execution_count": 3, "id": "db5e3098", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " id_booking number_of_applied_services \\\n", "0 919656 3 \n", "1 926634 3 \n", "2 931082 2 \n", "3 931086 2 \n", "4 931096 2 \n", "\n", " number_of_applied_upgraded_services number_of_applied_billable_services \\\n", "0 2 2 \n", "1 2 2 \n", "2 1 1 \n", "3 1 1 \n", "4 1 1 \n", "\n", " booking_days_to_check_in booking_number_of_nights \\\n", "0 87 4 \n", "1 109 3 \n", "2 50 7 \n", "3 15 3 \n", "4 8 5 \n", "\n", " has_verification_request has_billable_services \\\n", "0 False True \n", "1 False True \n", "2 False True \n", "3 False True \n", "4 False True \n", "\n", " has_upgraded_screening_service_business_type \\\n", "0 False \n", "1 False \n", "2 False \n", "3 False \n", "4 False \n", "\n", " has_deposit_management_service_business_type \\\n", "0 True \n", "1 True \n", "2 False \n", "3 False \n", "4 False \n", "\n", " has_protection_service_business_type has_resolution_incident \n", "0 True False \n", "1 True False \n", "2 True False \n", "3 True False \n", "4 True False \n", "Total Bookings: 16,193\n" ] } ], "source": [ "# Query to extract data\n", "data_extraction_query = \"\"\"\n", "select \n", " -- Unique ID --\n", " ibs.id_booking,\n", " -- Numeric Features --\n", " ibs.number_of_applied_services,\n", " ibs.number_of_applied_upgraded_services,\n", " ibs.number_of_applied_billable_services,\n", " ibs.booking_check_in_date_utc - booking_created_date_utc as booking_days_to_check_in,\n", " ibs.booking_number_of_nights,\n", " -- Categorical (Boolean) Features --\n", " ibs.has_verification_request,\n", " ibs.has_billable_services,\n", " ibs.has_upgraded_screening_service_business_type,\n", " ibs.has_deposit_management_service_business_type,\n", " ibs.has_protection_service_business_type,\n", " -- Target (Boolean) --\n", " ibs.has_resolution_incident\n", "from intermediate.int_booking_summary ibs\n", "where \n", " -- 1. Bookings from New Dash users with Id Deal\n", " ibs.is_user_in_new_dash = True and \n", " ibs.is_missing_id_deal = False and\n", " -- 2. Protected Bookings with a Protection or a Deposit Management service\n", " (ibs.has_protection_service_business_type or \n", " ibs.has_deposit_management_service_business_type) and\n", " -- 3. Bookings with flagging categorisation (this excludes Cancelled/Incomplete/Rejected bookings)\n", " ibs.is_booking_flagged_as_risk is not null and \n", " -- 4. Booking is completed\n", " ibs.is_booking_past_completion_date = True \n", "\"\"\"\n", "\n", "# Retrieve Data from Query\n", "df_extraction = query_to_dataframe(engine=dwh_pg_engine, query=data_extraction_query)\n", "print(df_extraction.head())\n", "print(f\"Total Bookings: {len(df_extraction):,}\")\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Processing\n", "Processing in this notebook is quite straight-forward: we just drop id booking, split the features and target and apply a scaling to numeric features.\n", "Afterwards, we split the dataset between train and test and display their sizes and target distribution." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training set size: 11335 rows\n", "Test set size: 4858 rows\n", "\n", "Training target distribution:\n", "has_resolution_incident\n", "False 0.988619\n", "True 0.011381\n", "Name: proportion, dtype: float64\n", "\n", "Test target distribution:\n", "has_resolution_incident\n", "False 0.988473\n", "True 0.011527\n", "Name: proportion, dtype: float64\n" ] } ], "source": [ "# Drop ID column\n", "df = df_extraction.copy().drop(columns=['id_booking'])\n", "\n", "# Separate features and target\n", "X = df.drop(columns=['has_resolution_incident'])\n", "y = df['has_resolution_incident']\n", "\n", "# Scale numeric features\n", "numeric_features = ['number_of_applied_services', \n", " 'booking_number_of_nights', \n", " 'number_of_applied_upgraded_services',\n", " 'number_of_applied_billable_services',\n", " 'booking_days_to_check_in']\n", "X[numeric_features] = X[numeric_features].astype(float)\n", "\n", "# Split the data\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size=0.3, random_state=123)\n", "\n", "print(f\"Training set size: {X_train.shape[0]} rows\")\n", "print(f\"Test set size: {X_test.shape[0]} rows\")\n", "\n", "print(\"\\nTraining target distribution:\")\n", "print(y_train.value_counts(normalize=True))\n", "\n", "print(\"\\nTest target distribution:\")\n", "print(y_test.value_counts(normalize=True))" ] }, { "cell_type": "markdown", "id": "d36c9276", "metadata": {}, "source": [ "## Classification Model with Random Forest\n", "\n", "We define a machine learning pipeline that includes:\n", "- **Scaling numeric features** with `StandardScaler`\n", "- **Training a Random Forest classifier** with balanced class weights to handle the imbalanced dataset\n", "\n", "We then use `GridSearchCV` to perform a **grid search with cross-validation** over a range of key hyperparameters (e.g., number of trees, max depth, etc.). \n", "The model is evaluated using **Average Precision**, which is better suited for imbalanced classification tasks.\n", "\n", "The best combination of parameters is selected, and the resulting model is used to make predictions on the test set.\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "943ef7d6", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 72 candidates, totalling 360 fits\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.6s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.6s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.1s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.1s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 3.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 4.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 2.1s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.2s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 6.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.6s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 6.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.7s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 6.8s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 3.0s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 2.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 3.0s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 3.0s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 4.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 3.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 2.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 4.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.1s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 7.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.1s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 6.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.0s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.8s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 2.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 4.1s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.1s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 6.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 6.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 3.0s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 4.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 3.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 2.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 2.2s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 6.8s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.8s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 7.1s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.8s\n", "[CV] END model__max_depth=None, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.0s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.1s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 3.0s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.9s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.9s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.1s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 2.0s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 5.4s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 5.6s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.1s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 5.2s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.9s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 5.4s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 5.3s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=10, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 2.0s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 5.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.9s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.8s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.8s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 4.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=10, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 3.2s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.0s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 3.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 3.2s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 5.0s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 5.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.0s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.0s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.1s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.8s\n", "[CV] END model__max_depth=20, model__max_features=sqrt, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 4.9s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=2, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=200; total time= 2.7s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 3.9s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.1s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=1, model__min_samples_split=5, model__n_estimators=300; total time= 4.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=200; total time= 2.9s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.4s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=100; total time= 1.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.8s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=2, model__n_estimators=300; total time= 3.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.3s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=200; total time= 2.2s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 2.8s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 2.8s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 2.6s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 2.5s\n", "[CV] END model__max_depth=20, model__max_features=log2, model__min_samples_leaf=2, model__min_samples_split=5, model__n_estimators=300; total time= 2.3s\n", "Best hyperparameters: {'model__max_depth': 10, 'model__max_features': 'sqrt', 'model__min_samples_leaf': 2, 'model__min_samples_split': 2, 'model__n_estimators': 100}\n" ] } ], "source": [ "\n", "# Define pipeline (scaling numeric features only)\n", "pipeline = Pipeline([\n", " ('scaler', StandardScaler()),\n", " ('model', RandomForestClassifier(class_weight='balanced', # We have an imbalanced dataset\n", " random_state=123))\n", "])\n", "\n", "# Define parameter grid\n", "param_grid = {\n", " 'model__n_estimators': [100, 200, 300],\n", " 'model__max_depth': [None, 10, 20],\n", " 'model__min_samples_split': [2, 5],\n", " 'model__min_samples_leaf': [1, 2],\n", " 'model__max_features': ['sqrt', 'log2']\n", "}\n", "\n", "# GridSearchCV\n", "grid_search = GridSearchCV(\n", " estimator=pipeline,\n", " param_grid=param_grid,\n", " scoring='average_precision', # For imbalanced classification\n", " cv=5, # 5-fold cross-validation\n", " n_jobs=-1, # Use all available cores\n", " verbose=2 # Verbose output for progress tracking\n", ")\n", "\n", "# Fit the grid search on training data\n", "grid_search.fit(X_train, y_train)\n", "\n", "# Best model\n", "best_pipeline = grid_search.best_estimator_\n", "print(\"Best hyperparameters:\", grid_search.best_params_)\n", "\n", "# Predict on test set\n", "y_pred_proba = best_pipeline.predict_proba(X_test)[:, 1]\n", "y_pred = best_pipeline.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
mean_fit_timestd_fit_timemean_score_timestd_score_timeparam_model__max_depthparam_model__max_featuresparam_model__min_samples_leafparam_model__min_samples_splitparam_model__n_estimatorsparamssplit0_test_scoresplit1_test_scoresplit2_test_scoresplit3_test_scoresplit4_test_scoremean_test_scorestd_test_scorerank_test_score
421.1916640.0608650.0602390.00391310log222100{'model__max_depth': 10, 'model__max_features'...0.0354310.0239020.0194520.0225380.0263370.0255320.0054261
301.2953140.2959650.0717690.01918510sqrt22100{'model__max_depth': 10, 'model__max_features'...0.0354310.0239020.0194520.0225380.0263370.0255320.0054261
312.3181250.1018940.1052940.00927310sqrt22200{'model__max_depth': 10, 'model__max_features'...0.0376340.0214050.0188780.0223860.0256250.0251860.0065893
432.5130330.1613500.1202590.02084110log222200{'model__max_depth': 10, 'model__max_features'...0.0376340.0214050.0188780.0223860.0256250.0251860.0065893
443.8620080.3697370.1707430.02973410log222300{'model__max_depth': 10, 'model__max_features'...0.0345150.0215610.0190280.0236100.0247280.0246880.0052835
.........................................................
144.7050511.0095300.2632260.106331Nonelog212300{'model__max_depth': None, 'model__max_feature...0.0287400.0150510.0152440.0180430.0129870.0180130.00559967
132.7781920.1753400.1217700.012860Nonelog212200{'model__max_depth': None, 'model__max_feature...0.0305430.0134190.0145270.0164480.0128570.0175590.00660769
13.2948910.4855180.1340530.017547Nonesqrt12200{'model__max_depth': None, 'model__max_feature...0.0305430.0134190.0145270.0164480.0128570.0175590.00660769
01.3166590.1086680.0640570.006920Nonesqrt12100{'model__max_depth': None, 'model__max_feature...0.0263170.0144950.0138190.0148430.0126230.0164190.00500771
121.4976230.3851280.0838250.028476Nonelog212100{'model__max_depth': None, 'model__max_feature...0.0263170.0144950.0138190.0148430.0126230.0164190.00500771
\n", "

72 rows × 18 columns

\n", "
" ], "text/plain": [ " mean_fit_time std_fit_time mean_score_time std_score_time \\\n", "42 1.191664 0.060865 0.060239 0.003913 \n", "30 1.295314 0.295965 0.071769 0.019185 \n", "31 2.318125 0.101894 0.105294 0.009273 \n", "43 2.513033 0.161350 0.120259 0.020841 \n", "44 3.862008 0.369737 0.170743 0.029734 \n", ".. ... ... ... ... \n", "14 4.705051 1.009530 0.263226 0.106331 \n", "13 2.778192 0.175340 0.121770 0.012860 \n", "1 3.294891 0.485518 0.134053 0.017547 \n", "0 1.316659 0.108668 0.064057 0.006920 \n", "12 1.497623 0.385128 0.083825 0.028476 \n", "\n", " param_model__max_depth param_model__max_features \\\n", "42 10 log2 \n", "30 10 sqrt \n", "31 10 sqrt \n", "43 10 log2 \n", "44 10 log2 \n", ".. ... ... \n", "14 None log2 \n", "13 None log2 \n", "1 None sqrt \n", "0 None sqrt \n", "12 None log2 \n", "\n", " param_model__min_samples_leaf param_model__min_samples_split \\\n", "42 2 2 \n", "30 2 2 \n", "31 2 2 \n", "43 2 2 \n", "44 2 2 \n", ".. ... ... \n", "14 1 2 \n", "13 1 2 \n", "1 1 2 \n", "0 1 2 \n", "12 1 2 \n", "\n", " param_model__n_estimators \\\n", "42 100 \n", "30 100 \n", "31 200 \n", "43 200 \n", "44 300 \n", ".. ... \n", "14 300 \n", "13 200 \n", "1 200 \n", "0 100 \n", "12 100 \n", "\n", " params split0_test_score \\\n", "42 {'model__max_depth': 10, 'model__max_features'... 0.035431 \n", "30 {'model__max_depth': 10, 'model__max_features'... 0.035431 \n", "31 {'model__max_depth': 10, 'model__max_features'... 0.037634 \n", "43 {'model__max_depth': 10, 'model__max_features'... 0.037634 \n", "44 {'model__max_depth': 10, 'model__max_features'... 0.034515 \n", ".. ... ... \n", "14 {'model__max_depth': None, 'model__max_feature... 0.028740 \n", "13 {'model__max_depth': None, 'model__max_feature... 0.030543 \n", "1 {'model__max_depth': None, 'model__max_feature... 0.030543 \n", "0 {'model__max_depth': None, 'model__max_feature... 0.026317 \n", "12 {'model__max_depth': None, 'model__max_feature... 0.026317 \n", "\n", " split1_test_score split2_test_score split3_test_score \\\n", "42 0.023902 0.019452 0.022538 \n", "30 0.023902 0.019452 0.022538 \n", "31 0.021405 0.018878 0.022386 \n", "43 0.021405 0.018878 0.022386 \n", "44 0.021561 0.019028 0.023610 \n", ".. ... ... ... \n", "14 0.015051 0.015244 0.018043 \n", "13 0.013419 0.014527 0.016448 \n", "1 0.013419 0.014527 0.016448 \n", "0 0.014495 0.013819 0.014843 \n", "12 0.014495 0.013819 0.014843 \n", "\n", " split4_test_score mean_test_score std_test_score rank_test_score \n", "42 0.026337 0.025532 0.005426 1 \n", "30 0.026337 0.025532 0.005426 1 \n", "31 0.025625 0.025186 0.006589 3 \n", "43 0.025625 0.025186 0.006589 3 \n", "44 0.024728 0.024688 0.005283 5 \n", ".. ... ... ... ... \n", "14 0.012987 0.018013 0.005599 67 \n", "13 0.012857 0.017559 0.006607 69 \n", "1 0.012857 0.017559 0.006607 69 \n", "0 0.012623 0.016419 0.005007 71 \n", "12 0.012623 0.016419 0.005007 71 \n", "\n", "[72 rows x 18 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Retrieve cv results\n", "pd.DataFrame(grid_search.cv_results_).sort_values(by='mean_test_score', ascending=False)" ] }, { "cell_type": "markdown", "id": "fc2fcc89", "metadata": {}, "source": [ "## Evaluation\n", "This section aims to evaluate how good the new model is vs. the actual Resolution Incidents.\n", "\n", "We start by computing and displaying the classification report, ROC Curve, PR Curve and the respective Area Under the Curve (AUC)." ] }, { "cell_type": "code", "execution_count": 7, "id": "30786f7c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " False 0.99 0.92 0.95 4802\n", " True 0.02 0.16 0.04 56\n", "\n", " accuracy 0.91 4858\n", " macro avg 0.51 0.54 0.49 4858\n", "weighted avg 0.98 0.91 0.94 4858\n", "\n" ] } ], "source": [ "# Print classification report\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpreting the Classification Report\n", "\n", "The **Classification Report** provides key metrics to evaluate how well the model performed on each class.\n", "\n", "It includes the following metrics for each class (0 and 1):\n", "* Metric: Meaning\n", "* Precision: Out of all predicted positives, how many were actually positive?\n", "* Recall: Out of all actual positives, how many did we correctly identify?\n", "* F1-score: Harmonic mean of precision and recall (balances both)\n", "* Support: Number of true samples of that class in the test data\n", "\n", "Interpretation:\n", "* Class 0 = No incident\n", "* Class 1 = Has resolution incident (rare, but important!)\n", "\n", "A few explanatory cases:\n", "* A high recall for class 1 means we're catching most incidents.\n", "* A high precision for class 1 means when we predict an incident, we're often correct.\n", "* The F1-score gives a single balanced measure (good for imbalanced data).\n", "\n", "Special note for imbalanced data:\n", "Since class 1 (or just True) is rare (1% in our case), metrics for that class are more critical.\n", "We want to maximize recall to catch as many real incidents as possible — without letting precision drop too low (to avoid too many false alarms)." ] }, { "cell_type": "code", "execution_count": 8, "id": "4b4da914", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# ROC Curve\n", "fpr, tpr, _ = roc_curve(y_test, y_pred_proba)\n", "roc_auc = auc(fpr, tpr)\n", "\n", "plt.figure(figsize=(6, 5))\n", "plt.plot(fpr, tpr, color='blue', lw=2, label=f'ROC curve (AUC = {roc_auc:.4f})')\n", "plt.plot([0, 1], [0, 1], color='gray', linestyle='--')\n", "plt.xlabel('False Positive Rate')\n", "plt.ylabel('True Positive Rate')\n", "plt.title('ROC Curve')\n", "plt.legend(loc='lower right')\n", "plt.grid(True)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpreting the ROC Curve\n", "\n", "The **Receiver Operating Characteristic (ROC) curve** shows how well the model distinguishes between the positive and negative classes across all decision thresholds.\n", "\n", "A quick reminder of the definitions:\n", "* True Positive Rate (TPR) = Recall\n", "* False Positive Rate (FPR) = Proportion of negatives wrongly classified as positives\n", "\n", "What we display in this plot is:\n", "* The x-axis is False Positive Rate\n", "* The y-axis is True Positive Rate\n", "\n", "The curve shows how TPR and FPR change as the threshold varies\n", "\n", "It's important to note that:\n", "* A model with no skill will produce a diagonal line (AUC = 0.5)\n", "* A model with perfect discrimination will hug the top-left corner (AUC = 1.0)\n", "\n", "The Area Under the Curve (ROC AUC) gives a single performance score:\n", "* Closer to 1 means better at ranking positive cases higher than negative ones\n", "\n", "**Important!**\n", "\n", "While useful, the ROC curve can sometimes overestimate performance when the dataset is imbalanced, because it includes negatives (which dominate in our case, around 99%!). That’s why we also MUST check the Precision-Recall curve." ] }, { "cell_type": "code", "execution_count": 9, "id": "6790d41d", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# PR Curve\n", "precision, recall, _ = precision_recall_curve(y_test, y_pred_proba)\n", "pr_auc = average_precision_score(y_test, y_pred_proba)\n", "\n", "plt.figure(figsize=(6, 5))\n", "plt.plot(recall, precision, color='green', lw=2, label=f'PR curve (AUC = {pr_auc:.4f})')\n", "plt.xlabel('Recall')\n", "plt.ylabel('Precision')\n", "plt.title('Precision-Recall Curve')\n", "plt.legend(loc='lower left')\n", "plt.grid(True)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpreting the Precision-Recall (PR) Curve\n", "\n", "The **Precision-Recall (PR) curve** helps evaluate model performance, especially on imbalanced datasets like ours (where positive cases are rare).\n", "\n", "A quick reminder of the definitions:\n", "* Precision = How many of the predicted positives are actually positive\n", "* Recall = How many of the actual positives the model correctly identifies\n", "\n", "What we display in this plot is:\n", "* The x-axis is Recall \n", "* The y-axis is Precision \n", "\n", "The curve shows the trade-off between them at different model thresholds\n", "\n", "In imbalanced datasets, accuracy can be misleading — the PR curve focuses only on the positive class, making it much more meaningful:\n", "* A higher curve means better performance\n", "* The area under the curve (PR AUC) summarizes this: closer to 1 is better" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Feature Importance\n", "Understanding what drives the prediction is useful for future experiments and business knowledge. Here we track both the native feature importances of the trees, as well as a more heavy SHAP values analysis.\n", "\n", "Important! Be aware that SHAP analysis might take quite a bit of time." ] }, { "cell_type": "code", "execution_count": 10, "id": "d66ffe2c", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "## BUILT-IN\n", "\n", "# Get feature importances from the model\n", "importances = best_pipeline.named_steps['model'].feature_importances_\n", "features = X.columns\n", "\n", "# Create a Series and sort\n", "feat_series = pd.Series(importances, index=features).sort_values(ascending=True) # ascending=True for horizontal plot\n", "\n", "# Plot Feature Importances\n", "plt.figure(figsize=(8, 5))\n", "feat_series.plot(kind='barh', color='skyblue')\n", "plt.title('Feature Importances')\n", "plt.xlabel('Importance')\n", "plt.grid(axis='x')\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpreting the Feature Importance Plot\n", "The **feature importance plot** shows how much each feature contributes to the model’s overall decision-making.\n", "\n", "For tree-based models like Random Forest, importance is based on how often and how effectively a feature is used to split the data across all trees.\n", "A higher score means the feature plays a bigger role in improving prediction accuracy.\n", "\n", "In the graph you will see that:\n", "* Features are ranked from most to least important.\n", "* The values are relative and model-specific — not directly interpretable as weights or probabilities.\n", "\n", "This helps us identify which features the model relies on most when making predictions.\n", "\n", "**Important!**\n", "Unlike SHAP values, native importance doesn't show how a feature affects predictions — only how useful it is to the model overall. For deeper interpretability (e.g., direction and context), SHAP is better (but it takes more time to run)." ] }, { "cell_type": "code", "execution_count": 11, "id": "e2197cea", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "ExactExplainer explainer: 4859it [09:15, 8.73it/s] \n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "## SHAP VALUES\n", "\n", "# SHAP requires that all features passed to Explainer be numeric (floats/ints)\n", "X_test_shap = X_test.copy()\n", "X_test_shap = X_test_shap.astype(float)\n", "\n", "# Function that returns the probability of the positive class\n", "def model_predict(data):\n", " return best_pipeline.predict_proba(data)[:, 1]\n", "\n", "# Ensure input to SHAP is numeric\n", "X_test_shap = X_test.astype(float)\n", "\n", "# Create SHAP explainer\n", "explainer = shap.Explainer(model_predict, X_test_shap)\n", "\n", "# Compute SHAP values\n", "shap_values = explainer(X_test_shap)\n", "\n", "# Plot summary\n", "shap.summary_plot(shap_values.values, X_test_shap)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpreting the SHAP Summary Plot\n", "\n", "Each point on a row represents a SHAP value for a single prediction (row = feature).\n", "The x-axis shows how much the feature contributed to increasing or decreasing the prediction.\n", "* Right (positive SHAP value): pushes prediction toward the positive class (i.e., higher chance of incident).\n", "* Left (negative SHAP value): pushes prediction toward the negative class (i.e., lower chance of incident).\n", "\n", "Color shows the actual feature value for that point:\n", "* Red = high value\n", "* Blue = low value\n", "\n", "In other words:\n", "* The position tells you impact.\n", "* The color tells you feature value.\n", "* The density (thickness) of dots shows how often a value occurs." ] } ], "metadata": { "kernelspec": { "display_name": "venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 5 }