Skip to content

Update decision tree ensemble notebook to not use exec #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update decision tree ensemble notebook to not use exec #1

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5557a0f
Update decision tree ensemble notebook to not use exec
teastburn Dec 23, 2023
bad8be6
Update decision_tree_ensembles/tree_ensemble_example.ipynb
teastburn Dec 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
196 changes: 23 additions & 173 deletions decision_tree_ensembles/tree_ensemble_example.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,29 +203,15 @@
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"clf = DecisionTreeClassifier(random_state=0)\n",
"clf = RandomForestClassifier(random_state=0)\n",
"clf = AdaBoostClassifier(random_state=0)\n",
"clf = GradientBoostingClassifier(random_state=0)\n"
]
}
],
"outputs": [],
"source": [
"clf_list = []\n",
"model_name_list = ['DecisionTreeClassifier', 'RandomForestClassifier', 'AdaBoostClassifier', 'GradientBoostingClassifier']\n",
"model_name_list = [DecisionTreeClassifier, RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier]\n",
"\n",
"# train model\n",
"for model_name in model_name_list:\n",
"\n",
" # dynamically write command to train each classifier in model_name_list\n",
" cmd = 'clf = ' + model_name + '(random_state=0)'\n",
" print(cmd) # print command\n",
" exec(cmd) # execute command\n",
" clf = model_name(random_state=0)\n",
" \n",
" # fit data to model\n",
" clf = clf.fit(X_train, y_train)\n",
Expand All @@ -241,12 +227,7 @@
"outputs": [
{
"data": {
"text/plain": [
"[DecisionTreeClassifier(random_state=0),\n",
" RandomForestClassifier(random_state=0),\n",
" AdaBoostClassifier(random_state=0),\n",
" GradientBoostingClassifier(random_state=0)]"
]
"text/plain": "[DecisionTreeClassifier(random_state=0),\n RandomForestClassifier(random_state=0),\n AdaBoostClassifier(random_state=0),\n GradientBoostingClassifier(random_state=0)]"
},
"execution_count": 11,
"metadata": {},
Expand All @@ -268,176 +249,45 @@
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"y_pred_train = clf.predict(X_train)\n",
"prec_val_list.append(precision_score(y_train, y_pred_train))\n",
"prec_val_list.append(recall_score(y_train, y_pred_train))\n",
"prec_val_list.append(f1_score(y_train, y_pred_train))\n",
"\n",
"y_pred_test = clf.predict(X_test)\n",
"prec_val_list.append(precision_score(y_test, y_pred_test))\n",
"prec_val_list.append(recall_score(y_test, y_pred_test))\n",
"prec_val_list.append(f1_score(y_test, y_pred_test))\n",
"\n",
"y_pred_train = clf.predict(X_train)\n",
"prec_val_list.append(precision_score(y_train, y_pred_train))\n",
"prec_val_list.append(recall_score(y_train, y_pred_train))\n",
"prec_val_list.append(f1_score(y_train, y_pred_train))\n",
"\n",
"y_pred_test = clf.predict(X_test)\n",
"prec_val_list.append(precision_score(y_test, y_pred_test))\n",
"prec_val_list.append(recall_score(y_test, y_pred_test))\n",
"prec_val_list.append(f1_score(y_test, y_pred_test))\n",
"\n",
"y_pred_train = clf.predict(X_train)\n",
"prec_val_list.append(precision_score(y_train, y_pred_train))\n",
"prec_val_list.append(recall_score(y_train, y_pred_train))\n",
"prec_val_list.append(f1_score(y_train, y_pred_train))\n",
"\n",
"y_pred_test = clf.predict(X_test)\n",
"prec_val_list.append(precision_score(y_test, y_pred_test))\n",
"prec_val_list.append(recall_score(y_test, y_pred_test))\n",
"prec_val_list.append(f1_score(y_test, y_pred_test))\n",
"\n",
"y_pred_train = clf.predict(X_train)\n",
"prec_val_list.append(precision_score(y_train, y_pred_train))\n",
"prec_val_list.append(recall_score(y_train, y_pred_train))\n",
"prec_val_list.append(f1_score(y_train, y_pred_train))\n",
"\n",
"y_pred_test = clf.predict(X_test)\n",
"prec_val_list.append(precision_score(y_test, y_pred_test))\n",
"prec_val_list.append(recall_score(y_test, y_pred_test))\n",
"prec_val_list.append(f1_score(y_test, y_pred_test))\n",
"\n"
]
}
],
"outputs": [],
"source": [
"performance_dict = {}\n",
"\n",
"dataset_name_list = ['train', 'test']\n",
"metric_name_list = ['precision', 'recall', 'f1']\n",
"dataset_list = [\n",
" (X_train, y_train, \"train\"),\n",
" (X_test, y_test, \"test\"),\n",
"]\n",
"metric_name_list = {precision_score: \"precision\", recall_score: \"recall\", f1_score: \"f1\"}\n",
"col_name_list = []\n",
"\n",
"for i in range(len(model_name_list)):\n",
" \n",
"\n",
" clf = clf_list[i]\n",
" \n",
"\n",
" prec_val_list = []\n",
" col_name_list = []\n",
" \n",
" for dataset_name in dataset_name_list:\n",
"\n",
" cmd = 'y_pred_' + dataset_name + ' = clf.predict(X_' + dataset_name + ')'\n",
" print(cmd)\n",
" exec(cmd)\n",
" \n",
" for metric_name in metric_name_list:\n",
" \n",
" cmd = 'prec_val_list.append(' + metric_name + '_score(y_' + dataset_name + ', y_pred_' + dataset_name + '))'\n",
" print(cmd)\n",
" exec(cmd)\n",
" for x_dataset, y_dataset, col_name in dataset_list:\n",
" y_pred = clf.predict(x_dataset)\n",
"\n",
" for metric_func, pretty_name in metric_name_list.items():\n",
" prec_val_list.append(metric_func(y_dataset, y_pred))\n",
" col_name_list.append(pretty_name + '_' + col_name)\n",
"\n",
" col_name_list.append(metric_name + '_' + dataset_name)\n",
" print('')\n",
" performance_dict[model_name_list[i].__name__] = prec_val_list\n",
"\n",
" performance_dict[model_name_list[i]] = prec_val_list\n",
" \n",
"df_performance = np.round(pd.DataFrame.from_dict(performance_dict, orient='index', columns=col_name_list),3)"
"df_performance = np.round(pd.DataFrame.from_dict(performance_dict, orient='index', columns=col_name_list),3)\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>precision_train</th>\n",
" <th>recall_train</th>\n",
" <th>f1_train</th>\n",
" <th>precision_test</th>\n",
" <th>recall_test</th>\n",
" <th>f1_test</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>DecisionTreeClassifier</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.952</td>\n",
" <td>0.896</td>\n",
" <td>0.923</td>\n",
" </tr>\n",
" <tr>\n",
" <th>RandomForestClassifier</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.985</td>\n",
" <td>0.955</td>\n",
" <td>0.970</td>\n",
" </tr>\n",
" <tr>\n",
" <th>AdaBoostClassifier</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.956</td>\n",
" <td>0.970</td>\n",
" <td>0.963</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GradientBoostingClassifier</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.970</td>\n",
" <td>0.970</td>\n",
" <td>0.970</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" precision_train recall_train f1_train \\\n",
"DecisionTreeClassifier 1.0 1.0 1.0 \n",
"RandomForestClassifier 1.0 1.0 1.0 \n",
"AdaBoostClassifier 1.0 1.0 1.0 \n",
"GradientBoostingClassifier 1.0 1.0 1.0 \n",
"\n",
" precision_test recall_test f1_test \n",
"DecisionTreeClassifier 0.952 0.896 0.923 \n",
"RandomForestClassifier 0.985 0.955 0.970 \n",
"AdaBoostClassifier 0.956 0.970 0.963 \n",
"GradientBoostingClassifier 0.970 0.970 0.970 "
]
"text/plain": " precision_train recall_train f1_train \\\nDecisionTreeClassifier 1.0 1.0 1.0 \nRandomForestClassifier 1.0 1.0 1.0 \nAdaBoostClassifier 1.0 1.0 1.0 \nGradientBoostingClassifier 1.0 1.0 1.0 \n\n precision_test recall_test f1_test \nDecisionTreeClassifier 0.952 0.896 0.923 \nRandomForestClassifier 0.985 0.955 0.970 \nAdaBoostClassifier 0.956 0.970 0.963 \nGradientBoostingClassifier 0.970 0.970 0.970 ",
Copy link
Author

@teastburn teastburn Dec 23, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i'm not sure why my pycharm/jupyter setup reformatted this. the previous formatting was more readable. but i wanted to be sure the correctness of the output was the same, so i included it here.

"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>precision_train</th>\n <th>recall_train</th>\n <th>f1_train</th>\n <th>precision_test</th>\n <th>recall_test</th>\n <th>f1_test</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>DecisionTreeClassifier</th>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.952</td>\n <td>0.896</td>\n <td>0.923</td>\n </tr>\n <tr>\n <th>RandomForestClassifier</th>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.985</td>\n <td>0.955</td>\n <td>0.970</td>\n </tr>\n <tr>\n <th>AdaBoostClassifier</th>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.956</td>\n <td>0.970</td>\n <td>0.963</td>\n </tr>\n <tr>\n <th>GradientBoostingClassifier</th>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.970</td>\n <td>0.970</td>\n <td>0.970</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"execution_count": 13,
"metadata": {},
Expand Down