Tabular Regression
Scikit-learn
random-forest
scikit-learn
shap
explainable-ai
public-health
air-quality
Instructions to use oukawa/PRISMA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use oukawa/PRISMA with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("oukawa/PRISMA", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Upload codes
Browse files
RF_spatial_explainability_all_diseases_and_groups.ipynb
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": null,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"colab": {
|
| 8 |
+
"base_uri": "https://localhost:8080/"
|
| 9 |
+
},
|
| 10 |
+
"executionInfo": {
|
| 11 |
+
"elapsed": 113875,
|
| 12 |
+
"status": "ok",
|
| 13 |
+
"timestamp": 1757816776531,
|
| 14 |
+
"user": {
|
| 15 |
+
"displayName": "Gabriel Oukawa",
|
| 16 |
+
"userId": "10622206185982477384"
|
| 17 |
+
},
|
| 18 |
+
"user_tz": 180
|
| 19 |
+
},
|
| 20 |
+
"id": "SzDbN-vemmfy",
|
| 21 |
+
"outputId": "7ef54d4c-7922-45bb-c9c5-2a4a0cad4abe"
|
| 22 |
+
},
|
| 23 |
+
"outputs": [],
|
| 24 |
+
"source": [
|
| 25 |
+
"# Libraries\n",
|
| 26 |
+
"import pandas as pd\n",
|
| 27 |
+
"import numpy as np\n",
|
| 28 |
+
"import pickle\n",
|
| 29 |
+
"import shap\n",
|
| 30 |
+
"import matplotlib.pyplot as plt"
|
| 31 |
+
]
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"cell_type": "code",
|
| 35 |
+
"execution_count": null,
|
| 36 |
+
"metadata": {},
|
| 37 |
+
"outputs": [],
|
| 38 |
+
"source": [
|
| 39 |
+
"# Load data and models\n",
|
| 40 |
+
"q = input('Load which matrix, 'lri', 'crd' or 'other'? ').strip().lower()\n",
|
| 41 |
+
"if q not in ['lri', 'crd', 'other']:\n",
|
| 42 |
+
" raise ValueError('Invalid input.')\n",
|
| 43 |
+
"\n",
|
| 44 |
+
"groups = ['general', 'g1', 'g2', 'g3']\n",
|
| 45 |
+
"data_path = '.../path/to/input/RF_spatial_data.csv'\n",
|
| 46 |
+
"df = pd.read_csv(data_path, delimiter=',', index_col=False)\n",
|
| 47 |
+
"\n",
|
| 48 |
+
"model_file = f'.../path/to/models/RF_spatial_{q.upper()}_admissions_per_1_million_all_groups.pkl'\n",
|
| 49 |
+
"with open(model_file, 'rb') as f:\n",
|
| 50 |
+
" all_models = pickle.load(f)\n",
|
| 51 |
+
"\n",
|
| 52 |
+
"shap_values_list, X_list, titles = [], [], []\n",
|
| 53 |
+
"\n",
|
| 54 |
+
"for g in groups:\n",
|
| 55 |
+
" col_name = f'{q.upper()}' if g == 'general' else f'{q.upper()}_{g.upper()}'\n",
|
| 56 |
+
" title = f'{q.upper()} - All Ages' if g == 'general' else f'{q.upper()} - Group {g[-1]}'\n",
|
| 57 |
+
" model_key = f'{q.upper()}_General' if g == 'general' else f'{q.upper()}_{g.upper()}'\n",
|
| 58 |
+
"\n",
|
| 59 |
+
" if col_name not in df.columns or model_key not in all_models:\n",
|
| 60 |
+
" continue\n",
|
| 61 |
+
"\n",
|
| 62 |
+
" model = all_models[model_key]\n",
|
| 63 |
+
" X = df.drop(columns=[c for c in df.columns if c.startswith(q.upper())])\n",
|
| 64 |
+
" explainer = shap.TreeExplainer(model)\n",
|
| 65 |
+
" shap_values = explainer.shap_values(X)\n",
|
| 66 |
+
"\n",
|
| 67 |
+
" shap_values_list.append(shap_values)\n",
|
| 68 |
+
" X_list.append(X)\n",
|
| 69 |
+
" titles.append(title)\n",
|
| 70 |
+
"\n",
|
| 71 |
+
" shap_df = pd.DataFrame(shap_values, columns=X.columns)\n",
|
| 72 |
+
" shap_df.to_csv(f\".../path/to/output/SHAP_{model_key}.csv\", index=False)"
|
| 73 |
+
]
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"cell_type": "code",
|
| 77 |
+
"execution_count": null,
|
| 78 |
+
"metadata": {},
|
| 79 |
+
"outputs": [],
|
| 80 |
+
"source": [
|
| 81 |
+
"# SHAP summary plots\n",
|
| 82 |
+
"fig, axes = plt.subplots(2, 2, figsize=(12, 10), dpi=600)\n",
|
| 83 |
+
"axes = axes.flatten()\n",
|
| 84 |
+
"\n",
|
| 85 |
+
"for i in range(len(shap_values_list)):\n",
|
| 86 |
+
" plt.sca(axes[i])\n",
|
| 87 |
+
" shap.summary_plot(shap_values_list[i], X_list[i], feature_names=X_list[i].columns, plot_type='dot', show=False, max_display=10)\n",
|
| 88 |
+
" ax = plt.gca()\n",
|
| 89 |
+
" ax.set_title(titles[i], fontsize=12)\n",
|
| 90 |
+
" ax.set_xlabel(ax.get_xlabel(), fontsize=12)\n",
|
| 91 |
+
" ax.tick_params(axis='both', which='major', labelsize=12)\n",
|
| 92 |
+
"\n",
|
| 93 |
+
"plt.tight_layout(pad=1.5)\n",
|
| 94 |
+
"plt.show()"
|
| 95 |
+
]
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"cell_type": "code",
|
| 99 |
+
"execution_count": null,
|
| 100 |
+
"metadata": {},
|
| 101 |
+
"outputs": [],
|
| 102 |
+
"source": [
|
| 103 |
+
"# SHAP dependence plots for top 10 features\n",
|
| 104 |
+
"mean_abs_shap = np.abs(shap_values.values).mean(axis=0)\n",
|
| 105 |
+
"top_features_idx = np.argsort(mean_abs_shap)[-10:][::-1]\n",
|
| 106 |
+
"top_features_names = [X.columns[i] for i in top_features_idx]\n",
|
| 107 |
+
"\n",
|
| 108 |
+
"fig, axes = plt.subplots(4, 2, figsize=(12, 16))\n",
|
| 109 |
+
"axes = axes.flatten()\n",
|
| 110 |
+
"for i, feature in enumerate(top_features_names):\n",
|
| 111 |
+
" shap.plots.scatter(shap_values[:, feature], ax=axes[i], show=False, color=shap_values)\n",
|
| 112 |
+
" axes[i].set_title(feature, fontsize=12)\n",
|
| 113 |
+
"\n",
|
| 114 |
+
"plt.tight_layout()\n",
|
| 115 |
+
"plt.show()"
|
| 116 |
+
]
|
| 117 |
+
}
|
| 118 |
+
],
|
| 119 |
+
"metadata": {
|
| 120 |
+
"colab": {
|
| 121 |
+
"provenance": [
|
| 122 |
+
{
|
| 123 |
+
"file_id": "1CTjVKHB6iiDvAQmm4JsyyIgVZShwcp_4",
|
| 124 |
+
"timestamp": 1723512979448
|
| 125 |
+
}
|
| 126 |
+
]
|
| 127 |
+
},
|
| 128 |
+
"kernelspec": {
|
| 129 |
+
"display_name": "Python 3",
|
| 130 |
+
"name": "python3"
|
| 131 |
+
},
|
| 132 |
+
"language_info": {
|
| 133 |
+
"name": "python"
|
| 134 |
+
}
|
| 135 |
+
},
|
| 136 |
+
"nbformat": 4,
|
| 137 |
+
"nbformat_minor": 0
|
| 138 |
+
}
|
RF_spatial_training_and_cross-validation_all_diseases_and_groups.ipynb
ADDED
|
@@ -0,0 +1,291 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": null,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"colab": {
|
| 8 |
+
"base_uri": "https://localhost:8080/"
|
| 9 |
+
},
|
| 10 |
+
"executionInfo": {
|
| 11 |
+
"elapsed": 113875,
|
| 12 |
+
"status": "ok",
|
| 13 |
+
"timestamp": 1757816776531,
|
| 14 |
+
"user": {
|
| 15 |
+
"displayName": "Gabriel Oukawa",
|
| 16 |
+
"userId": "10622206185982477384"
|
| 17 |
+
},
|
| 18 |
+
"user_tz": 180
|
| 19 |
+
},
|
| 20 |
+
"id": "SzDbN-vemmfy",
|
| 21 |
+
"outputId": "7ef54d4c-7922-45bb-c9c5-2a4a0cad4abe"
|
| 22 |
+
},
|
| 23 |
+
"outputs": [],
|
| 24 |
+
"source": [
|
| 25 |
+
"# Libraries\n",
|
| 26 |
+
"import pandas as pd\n",
|
| 27 |
+
"import numpy as np\n",
|
| 28 |
+
"import joblib\n",
|
| 29 |
+
"from pathlib import Path\n",
|
| 30 |
+
"from sklearn.ensemble import RandomForestRegressor\n",
|
| 31 |
+
"from sklearn.model_selection import train_test_split, GridSearchCV\n",
|
| 32 |
+
"from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score"
|
| 33 |
+
]
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"cell_type": "code",
|
| 37 |
+
"execution_count": null,
|
| 38 |
+
"metadata": {
|
| 39 |
+
"colab": {
|
| 40 |
+
"base_uri": "https://localhost:8080/"
|
| 41 |
+
},
|
| 42 |
+
"executionInfo": {
|
| 43 |
+
"elapsed": 184,
|
| 44 |
+
"status": "ok",
|
| 45 |
+
"timestamp": 1757816855352,
|
| 46 |
+
"user": {
|
| 47 |
+
"displayName": "Gabriel Oukawa",
|
| 48 |
+
"userId": "10622206185982477384"
|
| 49 |
+
},
|
| 50 |
+
"user_tz": 180
|
| 51 |
+
},
|
| 52 |
+
"id": "39d0a9OJqmxZ",
|
| 53 |
+
"outputId": "c100c3b4-66ef-4620-fbd2-25872d749deb"
|
| 54 |
+
},
|
| 55 |
+
"outputs": [],
|
| 56 |
+
"source": [
|
| 57 |
+
"# Load input data\n",
|
| 58 |
+
"data_path = '.../path/to/input/RF_spatial_data.csv'\n",
|
| 59 |
+
"df = pd.read_csv(data_path, delimiter=',', index_col=False)\n",
|
| 60 |
+
"\n",
|
| 61 |
+
"df = df[(df['date'] >= '2003-01-01') &\n",
|
| 62 |
+
" (df['date'] <= '2017-12-31')].reset_index(drop=True)\n",
|
| 63 |
+
"\n",
|
| 64 |
+
"# print(df.head())\n",
|
| 65 |
+
"# print(df.shape)"
|
| 66 |
+
]
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"cell_type": "code",
|
| 70 |
+
"execution_count": null,
|
| 71 |
+
"metadata": {
|
| 72 |
+
"colab": {
|
| 73 |
+
"base_uri": "https://localhost:8080/"
|
| 74 |
+
},
|
| 75 |
+
"executionInfo": {
|
| 76 |
+
"elapsed": 6803,
|
| 77 |
+
"status": "ok",
|
| 78 |
+
"timestamp": 1757816916603,
|
| 79 |
+
"user": {
|
| 80 |
+
"displayName": "Gabriel Oukawa",
|
| 81 |
+
"userId": "10622206185982477384"
|
| 82 |
+
},
|
| 83 |
+
"user_tz": 180
|
| 84 |
+
},
|
| 85 |
+
"id": "YnEWfX0s_6QN",
|
| 86 |
+
"outputId": "3a892047-134b-4816-886f-7bedc7d0c9b1"
|
| 87 |
+
},
|
| 88 |
+
"outputs": [],
|
| 89 |
+
"source": [
|
| 90 |
+
"# Train the RF model, evaluate metrics and save it to a file (single run)\n",
|
| 91 |
+
"q = input(\"Load which matrix: 'lri', 'crd' or 'general'?\").strip().lower()\n",
|
| 92 |
+
"if q not in ['lri', 'crd', 'general']:\n",
|
| 93 |
+
" raise ValueError(\"Invalid option!\")\n",
|
| 94 |
+
"\n",
|
| 95 |
+
"if q == 'lri':\n",
|
| 96 |
+
" name = 'LRI'\n",
|
| 97 |
+
"elif q == 'crd':\n",
|
| 98 |
+
" name = 'CRD'\n",
|
| 99 |
+
"elif q == 'general':\n",
|
| 100 |
+
" name = 'Other'\n",
|
| 101 |
+
"\n",
|
| 102 |
+
"all_models = {}\n",
|
| 103 |
+
"\n",
|
| 104 |
+
"groups = ['all', 'g1', 'g2', 'g3']\n",
|
| 105 |
+
"\n",
|
| 106 |
+
"for g in groups:\n",
|
| 107 |
+
" if g == 'all':\n",
|
| 108 |
+
" col_name = f'{q}'\n",
|
| 109 |
+
" model_name = f'{name}_General'\n",
|
| 110 |
+
" else:\n",
|
| 111 |
+
" col_name = f'{q}_{g}'\n",
|
| 112 |
+
" model_name = f'{name}_{g.upper()}'\n",
|
| 113 |
+
"\n",
|
| 114 |
+
" Y = df[col_name]\n",
|
| 115 |
+
" drop_cols = ['date', 'Other', 'Other_G1', 'Other_G2', 'Other_G3',\n",
|
| 116 |
+
" 'LRI', 'LRI_G1', 'LRI_G2', 'LRI_G3',\n",
|
| 117 |
+
" 'CRD', 'CRD_G1', 'CRD_G2', 'CRD_G3']\n",
|
| 118 |
+
" X = df.drop(columns=[c for c in drop_cols if c in df.columns])\n",
|
| 119 |
+
"\n",
|
| 120 |
+
" X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)\n",
|
| 121 |
+
"\n",
|
| 122 |
+
" model = RandomForestRegressor(\n",
|
| 123 |
+
" n_estimators=500,\n",
|
| 124 |
+
" oob_score=False,\n",
|
| 125 |
+
" bootstrap=True,\n",
|
| 126 |
+
" max_depth=20,\n",
|
| 127 |
+
" max_features=None,\n",
|
| 128 |
+
" min_samples_leaf=1,\n",
|
| 129 |
+
" min_samples_split=2,\n",
|
| 130 |
+
" n_jobs=-1,\n",
|
| 131 |
+
" verbose=1\n",
|
| 132 |
+
" )\n",
|
| 133 |
+
"\n",
|
| 134 |
+
" model.fit(X_train, Y_train)\n",
|
| 135 |
+
" Y_pred = model.predict(X_test)\n",
|
| 136 |
+
"\n",
|
| 137 |
+
" rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 138 |
+
" mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 139 |
+
" r2 = r2_score(Y_test, Y_pred)\n",
|
| 140 |
+
"\n",
|
| 141 |
+
" print('RMSE:', rmse)\n",
|
| 142 |
+
" print('MAE:', mae)\n",
|
| 143 |
+
" print('R2:', r2)\n",
|
| 144 |
+
"\n",
|
| 145 |
+
" all_models[model_name] = model\n",
|
| 146 |
+
"\n",
|
| 147 |
+
"output_file = Path(f'RF_spatial_{q.upper()}_all_groups.pkl')\n",
|
| 148 |
+
"joblib.dump(all_models, output_file)"
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"cell_type": "code",
|
| 153 |
+
"execution_count": null,
|
| 154 |
+
"metadata": {},
|
| 155 |
+
"outputs": [],
|
| 156 |
+
"source": [
|
| 157 |
+
"# Train the RF model and display scoring metrics (cross-validation)\n",
|
| 158 |
+
"q = input(\"Load which matrix: 'lri', 'crd' or 'general'?\").strip().lower()\n",
|
| 159 |
+
"if q not in ['lri', 'crd', 'general']:\n",
|
| 160 |
+
" raise ValueError(\"Invalid option!\")\n",
|
| 161 |
+
"\n",
|
| 162 |
+
"groups = ['all', 'g1', 'g2', 'g3']\n",
|
| 163 |
+
"results = []\n",
|
| 164 |
+
"\n",
|
| 165 |
+
"for g in groups:\n",
|
| 166 |
+
" if g == 'all':\n",
|
| 167 |
+
" col_name = f'{q}'\n",
|
| 168 |
+
" else:\n",
|
| 169 |
+
" col_name = f'{q}_{g}'\n",
|
| 170 |
+
" \n",
|
| 171 |
+
" Y = df[col_name]\n",
|
| 172 |
+
"\n",
|
| 173 |
+
" X = df.drop(columns=['date',\n",
|
| 174 |
+
" 'Other','Other_G1','Other_G2','Other_G3',\n",
|
| 175 |
+
" 'LRI','LRI_G1','LRI_G2','LRI_G3',\n",
|
| 176 |
+
" 'CRD','CRD_G1','CRD_G2','CRD_G3',\n",
|
| 177 |
+
" ])\n",
|
| 178 |
+
"\n",
|
| 179 |
+
" metrics_df = pd.DataFrame(columns=['R2', 'MAE', 'RMSE'])\n",
|
| 180 |
+
"\n",
|
| 181 |
+
" for i in range(100):\n",
|
| 182 |
+
" X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)\n",
|
| 183 |
+
"\n",
|
| 184 |
+
" model = RandomForestRegressor(\n",
|
| 185 |
+
" n_estimators=500,\n",
|
| 186 |
+
" oob_score=False,\n",
|
| 187 |
+
" bootstrap=True,\n",
|
| 188 |
+
" max_depth=20,\n",
|
| 189 |
+
" max_features=None,\n",
|
| 190 |
+
" min_samples_leaf=1,\n",
|
| 191 |
+
" min_samples_split=2,\n",
|
| 192 |
+
" n_jobs=-1,\n",
|
| 193 |
+
" verbose=1\n",
|
| 194 |
+
" )\n",
|
| 195 |
+
"\n",
|
| 196 |
+
" model.fit(X_train, Y_train)\n",
|
| 197 |
+
" Y_pred = model.predict(X_test)\n",
|
| 198 |
+
"\n",
|
| 199 |
+
" rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 200 |
+
" mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 201 |
+
" r2 = r2_score(Y_test, Y_pred)\n",
|
| 202 |
+
"\n",
|
| 203 |
+
" metrics_df.loc[i] = [r2, mae, rmse]\n",
|
| 204 |
+
"\n",
|
| 205 |
+
" summary = {\n",
|
| 206 |
+
" 'group': g,\n",
|
| 207 |
+
" 'R2_mean': metrics_df['R2'].mean(),\n",
|
| 208 |
+
" 'R2_min': metrics_df['R2'].min(),\n",
|
| 209 |
+
" 'R2_max': metrics_df['R2'].max(),\n",
|
| 210 |
+
" 'MAE_mean': metrics_df['MAE'].mean(),\n",
|
| 211 |
+
" 'MAE_min': metrics_df['MAE'].min(),\n",
|
| 212 |
+
" 'MAE_max': metrics_df['MAE'].max(),\n",
|
| 213 |
+
" 'RMSE_mean': metrics_df['RMSE'].mean(),\n",
|
| 214 |
+
" 'RMSE_min': metrics_df['RMSE'].min(),\n",
|
| 215 |
+
" 'RMSE_max': metrics_df['RMSE'].max()\n",
|
| 216 |
+
" }\n",
|
| 217 |
+
"\n",
|
| 218 |
+
" results.append(summary)\n",
|
| 219 |
+
"\n",
|
| 220 |
+
"summary_metrics = pd.DataFrame(results)\n",
|
| 221 |
+
"summary_metrics = summary_metrics.set_index('group')\n",
|
| 222 |
+
"\n",
|
| 223 |
+
"summary_metrics.head()"
|
| 224 |
+
]
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"cell_type": "code",
|
| 228 |
+
"execution_count": null,
|
| 229 |
+
"metadata": {},
|
| 230 |
+
"outputs": [],
|
| 231 |
+
"source": [
|
| 232 |
+
"# Test the best combination of hyperparameters\n",
|
| 233 |
+
"X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42) # Keep results reproducible\n",
|
| 234 |
+
"\n",
|
| 235 |
+
"param_grid = {\n",
|
| 236 |
+
" 'n_estimators': [100, 250, 500, 750],\n",
|
| 237 |
+
" 'max_depth': [10, 20, 30, None],\n",
|
| 238 |
+
" 'min_samples_leaf': [1, 2, 5],\n",
|
| 239 |
+
" 'min_samples_split': [2, 5, 10],\n",
|
| 240 |
+
" 'max_features': ['sqrt', 'log2', 0.3, None],\n",
|
| 241 |
+
" 'bootstrap': [True, False]\n",
|
| 242 |
+
"}\n",
|
| 243 |
+
"\n",
|
| 244 |
+
"rf = RandomForestRegressor(oob_score=False, n_jobs=-1, random_state=42)\n",
|
| 245 |
+
"\n",
|
| 246 |
+
"grid_search = GridSearchCV(\n",
|
| 247 |
+
" estimator=rf,\n",
|
| 248 |
+
" param_grid=param_grid,\n",
|
| 249 |
+
" scoring='r2',\n",
|
| 250 |
+
" cv=5,\n",
|
| 251 |
+
" verbose=1,\n",
|
| 252 |
+
" n_jobs=-1\n",
|
| 253 |
+
")\n",
|
| 254 |
+
"\n",
|
| 255 |
+
"grid_search.fit(X_train, Y_train)\n",
|
| 256 |
+
"\n",
|
| 257 |
+
"best_model = grid_search.best_estimator_\n",
|
| 258 |
+
"print(grid_search.best_params_)\n",
|
| 259 |
+
"\n",
|
| 260 |
+
"Y_pred = best_model.predict(X_test)\n",
|
| 261 |
+
"\n",
|
| 262 |
+
"r2 = r2_score(Y_test, Y_pred)\n",
|
| 263 |
+
"rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 264 |
+
"mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 265 |
+
"\n",
|
| 266 |
+
"print(f'R2: {r2:.4f}')\n",
|
| 267 |
+
"print(f'RMSE: {rmse:.4f}')\n",
|
| 268 |
+
"print(f'MAE: {mae:.4f}')"
|
| 269 |
+
]
|
| 270 |
+
}
|
| 271 |
+
],
|
| 272 |
+
"metadata": {
|
| 273 |
+
"colab": {
|
| 274 |
+
"provenance": [
|
| 275 |
+
{
|
| 276 |
+
"file_id": "1CTjVKHB6iiDvAQmm4JsyyIgVZShwcp_4",
|
| 277 |
+
"timestamp": 1723512979448
|
| 278 |
+
}
|
| 279 |
+
]
|
| 280 |
+
},
|
| 281 |
+
"kernelspec": {
|
| 282 |
+
"display_name": "Python 3",
|
| 283 |
+
"name": "python3"
|
| 284 |
+
},
|
| 285 |
+
"language_info": {
|
| 286 |
+
"name": "python"
|
| 287 |
+
}
|
| 288 |
+
},
|
| 289 |
+
"nbformat": 4,
|
| 290 |
+
"nbformat_minor": 0
|
| 291 |
+
}
|
RF_temporal_explainability_all_diseases_and_groups.ipynb
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": null,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"colab": {
|
| 8 |
+
"base_uri": "https://localhost:8080/"
|
| 9 |
+
},
|
| 10 |
+
"executionInfo": {
|
| 11 |
+
"elapsed": 71182,
|
| 12 |
+
"status": "ok",
|
| 13 |
+
"timestamp": 1756577181867,
|
| 14 |
+
"user": {
|
| 15 |
+
"displayName": "Gabriel Oukawa",
|
| 16 |
+
"userId": "10622206185982477384"
|
| 17 |
+
},
|
| 18 |
+
"user_tz": 180
|
| 19 |
+
},
|
| 20 |
+
"id": "SzDbN-vemmfy",
|
| 21 |
+
"outputId": "593926d4-0a36-4539-9b3f-e297ad04286f"
|
| 22 |
+
},
|
| 23 |
+
"outputs": [],
|
| 24 |
+
"source": [
|
| 25 |
+
"# Libraries\n",
|
| 26 |
+
"import pandas as pd\n",
|
| 27 |
+
"import numpy as np\n",
|
| 28 |
+
"import pickle\n",
|
| 29 |
+
"import shap\n",
|
| 30 |
+
"import matplotlib.pyplot as plt"
|
| 31 |
+
]
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"cell_type": "code",
|
| 35 |
+
"execution_count": null,
|
| 36 |
+
"metadata": {
|
| 37 |
+
"colab": {
|
| 38 |
+
"base_uri": "https://localhost:8080/"
|
| 39 |
+
},
|
| 40 |
+
"executionInfo": {
|
| 41 |
+
"elapsed": 2553,
|
| 42 |
+
"status": "ok",
|
| 43 |
+
"timestamp": 1756577184414,
|
| 44 |
+
"user": {
|
| 45 |
+
"displayName": "Gabriel Oukawa",
|
| 46 |
+
"userId": "10622206185982477384"
|
| 47 |
+
},
|
| 48 |
+
"user_tz": 180
|
| 49 |
+
},
|
| 50 |
+
"id": "39d0a9OJqmxZ",
|
| 51 |
+
"outputId": "32637b91-7b6e-46cb-ebf5-8252caf03cd0"
|
| 52 |
+
},
|
| 53 |
+
"outputs": [],
|
| 54 |
+
"source": [
|
| 55 |
+
"# Load data and models\n",
|
| 56 |
+
"q = input('Load which matrix, 'lri', 'crd' or 'other'? ').strip().lower()\n",
|
| 57 |
+
"if q not in ['lri', 'crd', 'other']:\n",
|
| 58 |
+
" raise ValueError('Invalid input.')\n",
|
| 59 |
+
"\n",
|
| 60 |
+
"groups = ['general', 'g1', 'g2', 'g3']\n",
|
| 61 |
+
"data_path = '.../path/to/input/RF_temporal_data.csv'\n",
|
| 62 |
+
"df = pd.read_csv(data_path, delimiter=',', index_col=False)\n",
|
| 63 |
+
"\n",
|
| 64 |
+
"model_file = f'.../path/to/models/RF_temporal_{q.upper()}_admissions_per_1_million_all_groups.pkl'\n",
|
| 65 |
+
"with open(model_file, 'rb') as f:\n",
|
| 66 |
+
" all_models = pickle.load(f)\n",
|
| 67 |
+
"\n",
|
| 68 |
+
"shap_values_list, X_list, titles = [], [], []\n",
|
| 69 |
+
"\n",
|
| 70 |
+
"for g in groups:\n",
|
| 71 |
+
" col_name = f'{q.upper()}' if g == 'general' else f'{q.upper()}_{g.upper()}'\n",
|
| 72 |
+
" title = f'{q.upper()} - All Ages' if g == 'general' else f'{q.upper()} - Group {g[-1]}'\n",
|
| 73 |
+
" model_key = f'{q.upper()}_General' if g == 'general' else f'{q.upper()}_{g.upper()}'\n",
|
| 74 |
+
"\n",
|
| 75 |
+
" if col_name not in df.columns or model_key not in all_models:\n",
|
| 76 |
+
" continue\n",
|
| 77 |
+
"\n",
|
| 78 |
+
" model = all_models[model_key]\n",
|
| 79 |
+
" X = df.drop(columns=[c for c in df.columns if c.startswith(q.upper())])\n",
|
| 80 |
+
" explainer = shap.TreeExplainer(model)\n",
|
| 81 |
+
" shap_values = explainer.shap_values(X)\n",
|
| 82 |
+
"\n",
|
| 83 |
+
" shap_values_list.append(shap_values)\n",
|
| 84 |
+
" X_list.append(X)\n",
|
| 85 |
+
" titles.append(title)\n",
|
| 86 |
+
"\n",
|
| 87 |
+
" shap_df = pd.DataFrame(shap_values, columns=X.columns)\n",
|
| 88 |
+
" shap_df.to_csv(f\".../path/to/output/SHAP_{model_key}.csv\", index=False)"
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"cell_type": "code",
|
| 93 |
+
"execution_count": null,
|
| 94 |
+
"metadata": {},
|
| 95 |
+
"outputs": [],
|
| 96 |
+
"source": [
|
| 97 |
+
"# SHAP summary plots\n",
|
| 98 |
+
"fig, axes = plt.subplots(2, 2, figsize=(12, 10), dpi=600)\n",
|
| 99 |
+
"axes = axes.flatten()\n",
|
| 100 |
+
"\n",
|
| 101 |
+
"for i in range(len(shap_values_list)):\n",
|
| 102 |
+
" plt.sca(axes[i])\n",
|
| 103 |
+
" shap.summary_plot(shap_values_list[i], X_list[i], feature_names=X_list[i].columns, plot_type='dot', show=False, max_display=10)\n",
|
| 104 |
+
" ax = plt.gca()\n",
|
| 105 |
+
" ax.set_title(titles[i], fontsize=12)\n",
|
| 106 |
+
" ax.set_xlabel(ax.get_xlabel(), fontsize=12)\n",
|
| 107 |
+
" ax.tick_params(axis='both', which='major', labelsize=12)\n",
|
| 108 |
+
"\n",
|
| 109 |
+
"plt.tight_layout(pad=1.5)\n",
|
| 110 |
+
"plt.show()"
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"cell_type": "code",
|
| 115 |
+
"execution_count": null,
|
| 116 |
+
"metadata": {},
|
| 117 |
+
"outputs": [],
|
| 118 |
+
"source": [
|
| 119 |
+
"# SHAP dependence plots for top 10 features\n",
|
| 120 |
+
"mean_abs_shap = np.abs(shap_values.values).mean(axis=0)\n",
|
| 121 |
+
"top_features_idx = np.argsort(mean_abs_shap)[-10:][::-1]\n",
|
| 122 |
+
"top_features_names = [X.columns[i] for i in top_features_idx]\n",
|
| 123 |
+
"\n",
|
| 124 |
+
"fig, axes = plt.subplots(4, 2, figsize=(12, 16))\n",
|
| 125 |
+
"axes = axes.flatten()\n",
|
| 126 |
+
"for i, feature in enumerate(top_features_names):\n",
|
| 127 |
+
" shap.plots.scatter(shap_values[:, feature], ax=axes[i], show=False, color=shap_values)\n",
|
| 128 |
+
" axes[i].set_title(feature, fontsize=12)\n",
|
| 129 |
+
"\n",
|
| 130 |
+
"plt.tight_layout()\n",
|
| 131 |
+
"plt.show()"
|
| 132 |
+
]
|
| 133 |
+
}
|
| 134 |
+
],
|
| 135 |
+
"metadata": {
|
| 136 |
+
"colab": {
|
| 137 |
+
"provenance": [
|
| 138 |
+
{
|
| 139 |
+
"file_id": "1CTjVKHB6iiDvAQmm4JsyyIgVZShwcp_4",
|
| 140 |
+
"timestamp": 1723512979448
|
| 141 |
+
}
|
| 142 |
+
]
|
| 143 |
+
},
|
| 144 |
+
"kernelspec": {
|
| 145 |
+
"display_name": "Python 3",
|
| 146 |
+
"name": "python3"
|
| 147 |
+
},
|
| 148 |
+
"language_info": {
|
| 149 |
+
"name": "python"
|
| 150 |
+
}
|
| 151 |
+
},
|
| 152 |
+
"nbformat": 4,
|
| 153 |
+
"nbformat_minor": 0
|
| 154 |
+
}
|
RF_temporal_training_and_cross-validation_all_diseases_and_groups.ipynb
ADDED
|
@@ -0,0 +1,310 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": null,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"colab": {
|
| 8 |
+
"base_uri": "https://localhost:8080/"
|
| 9 |
+
},
|
| 10 |
+
"executionInfo": {
|
| 11 |
+
"elapsed": 71182,
|
| 12 |
+
"status": "ok",
|
| 13 |
+
"timestamp": 1756577181867,
|
| 14 |
+
"user": {
|
| 15 |
+
"displayName": "Gabriel Oukawa",
|
| 16 |
+
"userId": "10622206185982477384"
|
| 17 |
+
},
|
| 18 |
+
"user_tz": 180
|
| 19 |
+
},
|
| 20 |
+
"id": "SzDbN-vemmfy",
|
| 21 |
+
"outputId": "593926d4-0a36-4539-9b3f-e297ad04286f"
|
| 22 |
+
},
|
| 23 |
+
"outputs": [],
|
| 24 |
+
"source": [
|
| 25 |
+
"# Libraries\n",
|
| 26 |
+
"import pandas as pd\n",
|
| 27 |
+
"import numpy as np\n",
|
| 28 |
+
"import joblib\n",
|
| 29 |
+
"from pathlib import Path\n",
|
| 30 |
+
"from sklearn.ensemble import RandomForestRegressor\n",
|
| 31 |
+
"from sklearn.model_selection import train_test_split, GridSearchCV\n",
|
| 32 |
+
"from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score"
|
| 33 |
+
]
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"cell_type": "code",
|
| 37 |
+
"execution_count": null,
|
| 38 |
+
"metadata": {
|
| 39 |
+
"colab": {
|
| 40 |
+
"base_uri": "https://localhost:8080/"
|
| 41 |
+
},
|
| 42 |
+
"executionInfo": {
|
| 43 |
+
"elapsed": 2553,
|
| 44 |
+
"status": "ok",
|
| 45 |
+
"timestamp": 1756577184414,
|
| 46 |
+
"user": {
|
| 47 |
+
"displayName": "Gabriel Oukawa",
|
| 48 |
+
"userId": "10622206185982477384"
|
| 49 |
+
},
|
| 50 |
+
"user_tz": 180
|
| 51 |
+
},
|
| 52 |
+
"id": "39d0a9OJqmxZ",
|
| 53 |
+
"outputId": "32637b91-7b6e-46cb-ebf5-8252caf03cd0"
|
| 54 |
+
},
|
| 55 |
+
"outputs": [],
|
| 56 |
+
"source": [
|
| 57 |
+
"# Load input data\n",
|
| 58 |
+
"data_path = '.../path/to/input/RF_temporal_data.csv'\n",
|
| 59 |
+
"df = pd.read_csv(data_path, delimiter=',', index_col=False)\n",
|
| 60 |
+
"\n",
|
| 61 |
+
"df = df[(df['date'] >= '2003-01-01') &\n",
|
| 62 |
+
" (df['date'] <= '2017-12-31')].reset_index(drop=True)\n",
|
| 63 |
+
"\n",
|
| 64 |
+
"# print(df.head())\n",
|
| 65 |
+
"# print(df.shape)"
|
| 66 |
+
]
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"cell_type": "code",
|
| 70 |
+
"execution_count": null,
|
| 71 |
+
"metadata": {
|
| 72 |
+
"colab": {
|
| 73 |
+
"base_uri": "https://localhost:8080/"
|
| 74 |
+
},
|
| 75 |
+
"executionInfo": {
|
| 76 |
+
"elapsed": 8823,
|
| 77 |
+
"status": "ok",
|
| 78 |
+
"timestamp": 1756494244204,
|
| 79 |
+
"user": {
|
| 80 |
+
"displayName": "Gabriel Oukawa",
|
| 81 |
+
"userId": "10622206185982477384"
|
| 82 |
+
},
|
| 83 |
+
"user_tz": 180
|
| 84 |
+
},
|
| 85 |
+
"id": "YnEWfX0s_6QN",
|
| 86 |
+
"outputId": "b00bf703-980a-433d-cbf1-950c9ebd978a"
|
| 87 |
+
},
|
| 88 |
+
"outputs": [],
|
| 89 |
+
"source": [
|
| 90 |
+
"# Train the RF model, evaluate metrics and save it to a file (single run)\n",
|
| 91 |
+
"q = input(\"Load which matrix: 'lri', 'crd' or 'general'?\").strip().lower()\n",
|
| 92 |
+
"if q not in ['lri', 'crd', 'general']:\n",
|
| 93 |
+
" raise ValueError(\"Invalid option!\")\n",
|
| 94 |
+
"\n",
|
| 95 |
+
"if q == 'lri':\n",
|
| 96 |
+
" name = 'LRI'\n",
|
| 97 |
+
"elif q == 'crd':\n",
|
| 98 |
+
" name = 'CRD'\n",
|
| 99 |
+
"elif q == 'general':\n",
|
| 100 |
+
" name = 'Other'\n",
|
| 101 |
+
"\n",
|
| 102 |
+
"all_models = {}\n",
|
| 103 |
+
"\n",
|
| 104 |
+
"groups = ['all', 'g1', 'g2', 'g3']\n",
|
| 105 |
+
"\n",
|
| 106 |
+
"for g in groups:\n",
|
| 107 |
+
" if g == 'all':\n",
|
| 108 |
+
" col_name = f'{q}'\n",
|
| 109 |
+
" model_name = f'{name}_General'\n",
|
| 110 |
+
" else:\n",
|
| 111 |
+
" col_name = f'{q}_{g}'\n",
|
| 112 |
+
" model_name = f'{name}_{g.upper()}'\n",
|
| 113 |
+
"\n",
|
| 114 |
+
" Y = df[col_name]\n",
|
| 115 |
+
" drop_cols = ['date', 'Other', 'Other_G1', 'Other_G2', 'Other_G3',\n",
|
| 116 |
+
" 'LRI', 'LRI_G1', 'LRI_G2', 'LRI_G3',\n",
|
| 117 |
+
" 'CRD', 'CRD_G1', 'CRD_G2', 'CRD_G3']\n",
|
| 118 |
+
" X = df.drop(columns=[c for c in drop_cols if c in df.columns])\n",
|
| 119 |
+
"\n",
|
| 120 |
+
" X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)\n",
|
| 121 |
+
"\n",
|
| 122 |
+
" model = RandomForestRegressor(\n",
|
| 123 |
+
" n_estimators=500,\n",
|
| 124 |
+
" oob_score=False,\n",
|
| 125 |
+
" bootstrap=True,\n",
|
| 126 |
+
" max_depth=20,\n",
|
| 127 |
+
" max_features=None,\n",
|
| 128 |
+
" min_samples_leaf=1,\n",
|
| 129 |
+
" min_samples_split=2,\n",
|
| 130 |
+
" n_jobs=-1,\n",
|
| 131 |
+
" verbose=1\n",
|
| 132 |
+
" )\n",
|
| 133 |
+
"\n",
|
| 134 |
+
" model.fit(X_train, Y_train)\n",
|
| 135 |
+
" Y_pred = model.predict(X_test)\n",
|
| 136 |
+
"\n",
|
| 137 |
+
" rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 138 |
+
" mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 139 |
+
" r2 = r2_score(Y_test, Y_pred)\n",
|
| 140 |
+
"\n",
|
| 141 |
+
" print('RMSE:', rmse)\n",
|
| 142 |
+
" print('MAE:', mae)\n",
|
| 143 |
+
" print('R2:', r2)\n",
|
| 144 |
+
"\n",
|
| 145 |
+
" all_models[model_name] = model\n",
|
| 146 |
+
"\n",
|
| 147 |
+
"output_file = Path(f'RF_temporal_{q.upper()}_all_groups.pkl')\n",
|
| 148 |
+
"joblib.dump(all_models, output_file)"
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"cell_type": "code",
|
| 153 |
+
"execution_count": null,
|
| 154 |
+
"metadata": {
|
| 155 |
+
"colab": {
|
| 156 |
+
"base_uri": "https://localhost:8080/",
|
| 157 |
+
"height": 206
|
| 158 |
+
},
|
| 159 |
+
"executionInfo": {
|
| 160 |
+
"elapsed": 269201,
|
| 161 |
+
"status": "ok",
|
| 162 |
+
"timestamp": 1756496620139,
|
| 163 |
+
"user": {
|
| 164 |
+
"displayName": "Gabriel Oukawa",
|
| 165 |
+
"userId": "10622206185982477384"
|
| 166 |
+
},
|
| 167 |
+
"user_tz": 180
|
| 168 |
+
},
|
| 169 |
+
"id": "deeVkaRIv5II",
|
| 170 |
+
"outputId": "a9d76df9-208e-4e67-8cdc-4c70d4b20fcc"
|
| 171 |
+
},
|
| 172 |
+
"outputs": [],
|
| 173 |
+
"source": [
|
| 174 |
+
"# Train the RF model and display scoring metrics (cross-validation)\n",
|
| 175 |
+
"q = input(\"Load which matrix: 'lri', 'crd' or 'general'?\").strip().lower()\n",
|
| 176 |
+
"if q not in ['lri', 'crd', 'general']:\n",
|
| 177 |
+
" raise ValueError(\"Invalid option!\")\n",
|
| 178 |
+
"\n",
|
| 179 |
+
"groups = ['all', 'g1', 'g2', 'g3']\n",
|
| 180 |
+
"results = []\n",
|
| 181 |
+
"\n",
|
| 182 |
+
"for g in groups:\n",
|
| 183 |
+
" if g == 'all':\n",
|
| 184 |
+
" col_name = f'{q}'\n",
|
| 185 |
+
" else:\n",
|
| 186 |
+
" col_name = f'{q}_{g}'\n",
|
| 187 |
+
" \n",
|
| 188 |
+
" Y = df[col_name]\n",
|
| 189 |
+
"\n",
|
| 190 |
+
" X = df.drop(columns=['date',\n",
|
| 191 |
+
" 'Other','Other_G1','Other_G2','Other_G3',\n",
|
| 192 |
+
" 'LRI','LRI_G1','LRI_G2','LRI_G3',\n",
|
| 193 |
+
" 'CRD','CRD_G1','CRD_G2','CRD_G3',\n",
|
| 194 |
+
" ])\n",
|
| 195 |
+
"\n",
|
| 196 |
+
" metrics_df = pd.DataFrame(columns=['R2', 'MAE', 'RMSE'])\n",
|
| 197 |
+
"\n",
|
| 198 |
+
" for i in range(100):\n",
|
| 199 |
+
" X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)\n",
|
| 200 |
+
"\n",
|
| 201 |
+
" model = RandomForestRegressor(\n",
|
| 202 |
+
" n_estimators=500,\n",
|
| 203 |
+
" oob_score=False,\n",
|
| 204 |
+
" bootstrap=True,\n",
|
| 205 |
+
" max_depth=20,\n",
|
| 206 |
+
" max_features=None,\n",
|
| 207 |
+
" min_samples_leaf=1,\n",
|
| 208 |
+
" min_samples_split=2,\n",
|
| 209 |
+
" n_jobs=-1,\n",
|
| 210 |
+
" verbose=1\n",
|
| 211 |
+
" )\n",
|
| 212 |
+
"\n",
|
| 213 |
+
" model.fit(X_train, Y_train)\n",
|
| 214 |
+
" Y_pred = model.predict(X_test)\n",
|
| 215 |
+
"\n",
|
| 216 |
+
" rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 217 |
+
" mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 218 |
+
" r2 = r2_score(Y_test, Y_pred)\n",
|
| 219 |
+
"\n",
|
| 220 |
+
" metrics_df.loc[i] = [r2, mae, rmse]\n",
|
| 221 |
+
"\n",
|
| 222 |
+
" summary = {\n",
|
| 223 |
+
" 'group': g,\n",
|
| 224 |
+
" 'R2_mean': metrics_df['R2'].mean(),\n",
|
| 225 |
+
" 'R2_min': metrics_df['R2'].min(),\n",
|
| 226 |
+
" 'R2_max': metrics_df['R2'].max(),\n",
|
| 227 |
+
" 'MAE_mean': metrics_df['MAE'].mean(),\n",
|
| 228 |
+
" 'MAE_min': metrics_df['MAE'].min(),\n",
|
| 229 |
+
" 'MAE_max': metrics_df['MAE'].max(),\n",
|
| 230 |
+
" 'RMSE_mean': metrics_df['RMSE'].mean(),\n",
|
| 231 |
+
" 'RMSE_min': metrics_df['RMSE'].min(),\n",
|
| 232 |
+
" 'RMSE_max': metrics_df['RMSE'].max()\n",
|
| 233 |
+
" }\n",
|
| 234 |
+
"\n",
|
| 235 |
+
" results.append(summary)\n",
|
| 236 |
+
"\n",
|
| 237 |
+
"summary_metrics = pd.DataFrame(results)\n",
|
| 238 |
+
"summary_metrics = summary_metrics.set_index('group')\n",
|
| 239 |
+
"\n",
|
| 240 |
+
"summary_metrics.head()"
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"cell_type": "code",
|
| 245 |
+
"execution_count": null,
|
| 246 |
+
"metadata": {
|
| 247 |
+
"id": "FGjVNw-bCUJi"
|
| 248 |
+
},
|
| 249 |
+
"outputs": [],
|
| 250 |
+
"source": [
|
| 251 |
+
"# Test the best combination of hyperparameters\n",
|
| 252 |
+
"X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42) # Keep results reproducible\n",
|
| 253 |
+
"\n",
|
| 254 |
+
"param_grid = {\n",
|
| 255 |
+
" 'n_estimators': [100, 250, 500, 750],\n",
|
| 256 |
+
" 'max_depth': [10, 20, 30, None],\n",
|
| 257 |
+
" 'min_samples_leaf': [1, 2, 5],\n",
|
| 258 |
+
" 'min_samples_split': [2, 5, 10],\n",
|
| 259 |
+
" 'max_features': ['sqrt', 'log2', 0.3, None],\n",
|
| 260 |
+
" 'bootstrap': [True, False]\n",
|
| 261 |
+
"}\n",
|
| 262 |
+
"\n",
|
| 263 |
+
"rf = RandomForestRegressor(oob_score=False, n_jobs=-1, random_state=42)\n",
|
| 264 |
+
"\n",
|
| 265 |
+
"grid_search = GridSearchCV(\n",
|
| 266 |
+
" estimator=rf,\n",
|
| 267 |
+
" param_grid=param_grid,\n",
|
| 268 |
+
" scoring='r2',\n",
|
| 269 |
+
" cv=5,\n",
|
| 270 |
+
" verbose=1,\n",
|
| 271 |
+
" n_jobs=-1\n",
|
| 272 |
+
")\n",
|
| 273 |
+
"\n",
|
| 274 |
+
"grid_search.fit(X_train, Y_train)\n",
|
| 275 |
+
"\n",
|
| 276 |
+
"best_model = grid_search.best_estimator_\n",
|
| 277 |
+
"print(grid_search.best_params_)\n",
|
| 278 |
+
"\n",
|
| 279 |
+
"Y_pred = best_model.predict(X_test)\n",
|
| 280 |
+
"\n",
|
| 281 |
+
"r2 = r2_score(Y_test, Y_pred)\n",
|
| 282 |
+
"rmse = np.sqrt(mean_squared_error(Y_test, Y_pred))\n",
|
| 283 |
+
"mae = mean_absolute_error(Y_test, Y_pred)\n",
|
| 284 |
+
"\n",
|
| 285 |
+
"print(f'R2: {r2:.4f}')\n",
|
| 286 |
+
"print(f'RMSE: {rmse:.4f}')\n",
|
| 287 |
+
"print(f'MAE: {mae:.4f}')"
|
| 288 |
+
]
|
| 289 |
+
}
|
| 290 |
+
],
|
| 291 |
+
"metadata": {
|
| 292 |
+
"colab": {
|
| 293 |
+
"provenance": [
|
| 294 |
+
{
|
| 295 |
+
"file_id": "1CTjVKHB6iiDvAQmm4JsyyIgVZShwcp_4",
|
| 296 |
+
"timestamp": 1723512979448
|
| 297 |
+
}
|
| 298 |
+
]
|
| 299 |
+
},
|
| 300 |
+
"kernelspec": {
|
| 301 |
+
"display_name": "Python 3",
|
| 302 |
+
"name": "python3"
|
| 303 |
+
},
|
| 304 |
+
"language_info": {
|
| 305 |
+
"name": "python"
|
| 306 |
+
}
|
| 307 |
+
},
|
| 308 |
+
"nbformat": 4,
|
| 309 |
+
"nbformat_minor": 0
|
| 310 |
+
}
|