{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Supermarket Regression 2 Notebook"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"parameters"
]
},
"outputs": [],
"source": [
"dataset = \"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"dataset = pd.DataFrame.from_dict(json.loads(dataset))\n",
"y_target = dataset['Product_Supermarket_Sales']\n",
"dataset.drop(['Product_Supermarket_Sales'], axis=1, inplace=True)\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(dataset, y_target, test_size = 0.3)\n",
"\n",
"print(\"Training data is\", X_train.shape)\n",
"print(\"Training target is\", y_train.shape)\n",
"print(\"test data is\", X_test.shape)\n",
"print(\"test target is\", y_test.shape)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import RobustScaler, StandardScaler\n",
"scaler = RobustScaler()\n",
"\n",
"scaler.fit(X_train)\n",
"\n",
"X_train = scaler.transform(X_train) \n",
"X_test = scaler.transform(X_test)\n",
"\n",
"X_train[:5, :5]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import mean_absolute_error\n",
"from sklearn.model_selection import KFold, cross_val_score\n",
"\n",
"\n",
"def cross_validate(model, nfolds, feats, targets):\n",
" score = -1 * (cross_val_score(model, feats, targets, cv=nfolds, scoring='neg_mean_absolute_error'))\n",
" return np.mean(score)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"parameters"
]
},
"outputs": [],
"source": [
"n_estimators=150\n",
"max_depth=3\n",
"max_features='sqrt'\n",
"min_samples_split=4\n",
"random_state=2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.ensemble import GradientBoostingRegressor\n",
"\n",
"gb_model = GradientBoostingRegressor(n_estimators=n_estimators, max_depth=max_depth, max_features=max_features, min_samples_split=min_samples_split, random_state=random_state)\n",
"\n",
"mae_score = cross_validate(gb_model, 10, X_train, y_train)\n",
"print(\"MAE Score: \", mae_score)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"outputs"
]
},
"outputs": [],
"source": [
"from flytekitplugins.papermill import record_outputs\n",
"record_outputs(mae_score=float(mae_score))"
]
}
],
"metadata": {
"celltoolbar": "Tags",
"kernelspec": {
"display_name": "Python 3.9.9 64-bit ('flytesnacks')",
"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": "3.9.9"
},
"vscode": {
"interpreter": {
"hash": "93d1c4f33f306e18e1c08a771c972fe86afbedaedb2338666e30a98a5179caac"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}