{ "cells": [ { "cell_type": "code", "execution_count": null, "id": "zph67XPWcccE", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 397 }, "id": "zph67XPWcccE", "outputId": "a8079530-4fcc-40f3-dd22-4670b846ff74" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['Year', 'Land use', 'SITE', 'Latitude', 'Longitude', 'Address',\n", " 'Suburb', 'Local Government Area', 'Variable Units', 'Variable Value',\n", " 'Start Date', 'End Date', 'Average Weekday Volume',\n", " 'Average Weekend Volume', 'Weekday Peak Hour Start',\n", " 'Weekday Peak Hour End', 'Weekday Peak Volume',\n", " 'Weekend Peak Hour Start', 'Weekend Peak Hour End',\n", " 'Weekend Peak Volume'],\n", " dtype='object')\n", "Mean Squared Error: 7115.204403911587\n", "R² Score: 0.9684319620568578\n" ] }, { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"coef_df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"Feature\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Average Weekday Volume\",\n \"Year\",\n \"Average Weekend Volume\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Coefficient\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6965814812030052,\n \"min\": -0.3590248520297687,\n \"max\": 1.3638357782200983,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.07461407220555194,\n -0.3590248520297687,\n -0.07515772137801585\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "coef_df" }, "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", "
FeatureCoefficient
0Land use code1.363836
1Average Weekday Volume0.074614
2Average Weekend Volume-0.075158
3Weekend Peak Volume0.742084
4Year-0.359025
\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" ], "text/plain": [ " Feature Coefficient\n", "0 Land use code 1.363836\n", "1 Average Weekday Volume 0.074614\n", "2 Average Weekend Volume -0.075158\n", "3 Weekend Peak Volume 0.742084\n", "4 Year -0.359025" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Predicted Weekday Peak Volume: 118.24\n" ] } ], "source": [ "# Import libraries\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.linear_model import LinearRegression\n", "from sklearn.metrics import mean_squared_error, r2_score\n", "\n", "# Load the Queensland Traffic Generation Dataset\n", "url = \"https://www.data.qld.gov.au/dataset/cc4fbe7f-0d8e-4876-b309-a29b785149b4/resource/73079dc1-c34e-44cf-9e9a-8acb13591c1b/download/traffic-generation-data-site-summary.csv\"\n", "df = pd.read_csv(url)\n", "\n", "# Data Cleaning\n", "# Correct the column names in the subset argument to match the actual column names in the DataFrame\n", "# Print the columns to inspect their names\n", "print(df.columns)\n", "# Adjust the column names in subset based on the printed output\n", "df = df.dropna(subset=['Average Weekday Volume', 'Average Weekend Volume', 'Weekday Peak Volume', 'Weekend Peak Volume'])\n", "df = df[df['Land use'].notna()] # Filter valid land uses\n", "\n", "# Encode land use\n", "df['Land use code'] = df['Land use'].astype('category').cat.codes\n", "\n", "# Select relevant features\n", "X = df[['Land use code', 'Average Weekday Volume', 'Average Weekend Volume', 'Weekend Peak Volume', 'Year']] # Use corrected column names\n", "y = df['Weekday Peak Volume'] # Use corrected column name\n", "\n", "# Split data\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Train model\n", "model = LinearRegression()\n", "model.fit(X_train, y_train)\n", "\n", "# Predict & Evaluate\n", "y_pred = model.predict(X_test)\n", "print(\"Mean Squared Error:\", mean_squared_error(y_test, y_pred))\n", "print(\"R² Score:\", r2_score(y_test, y_pred))\n", "\n", "# Coefficients\n", "coef_df = pd.DataFrame({'Feature': X.columns, 'Coefficient': model.coef_})\n", "display(coef_df)\n", "\n", "# Predict for new input (example)\n", "example = pd.DataFrame([[3, 900, 750, 120, 2018]], columns=X.columns) # Use corrected column names\n", "predicted_peak = model.predict(example)\n", "print(f\"Predicted Weekday Peak Volume: {predicted_peak[0]:.2f}\")" ] }, { "cell_type": "code", "execution_count": 2, "id": "syZCgI2I80VY", "metadata": { "id": "syZCgI2I80VY" }, "outputs": [], "source": [] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 5 }