KDEPredictionModel

{"cells":[{"cell_type":"markdown","metadata":{"id":"OraMQ6PQrZdI"},"source":["Final Dataset Link: https://drive.google.com/file/d/14KpYro56AbayWBQZ6CJfootZ-lC_SseK/view?usp=sharing"]},{"cell_type":"markdown","metadata":{"id":"HAqzqLUCrxDJ"},"source":["# Import Packages"]},{"cell_type":"code","execution_count":1,"metadata":{"id":"lsdP-2xtrO20","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1733118042684,"user_tz":300,"elapsed":26281,"user":{"displayName":"Karuna Adhikari","userId":"14765861351042505468"}},"outputId":"0c6ff2f6-aba6-4f50-945d-328003e2d1bd"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: gdown in /usr/local/lib/python3.10/dist-packages (5.2.0)\n","Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from gdown) (4.12.3)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from gdown) (3.16.1)\n","Requirement already satisfied: requests[socks] in /usr/local/lib/python3.10/dist-packages (from gdown) (2.32.3)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from gdown) (4.66.6)\n","Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->gdown) (2.6)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (3.4.0)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (3.10)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (2.2.3)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (2024.8.30)\n","Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (1.7.1)\n"]}],"source":["# install the gdown package in Colab\n","!pip install gdown\n","import pandas as pd\n","import numpy as np\n","import gdown\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","import folium\n","import geopandas as gpd\n","from sklearn.neighbors import KernelDensity"]},{"cell_type":"markdown","metadata":{"id":"WAErLXGardwU"},"source":["# Import Dataset\n"]},{"cell_type":"code","execution_count":2,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":104},"executionInfo":{"elapsed":3849,"status":"ok","timestamp":1733118046522,"user":{"displayName":"Karuna Adhikari","userId":"14765861351042505468"},"user_tz":300},"id":"jHeHMMjHrdAU","outputId":"2a7ab266-20db-4010-94a7-8f54668b9cd6"},"outputs":[{"output_type":"stream","name":"stderr","text":["Downloading...\n","From: https://drive.google.com/uc?id=14KpYro56AbayWBQZ6CJfootZ-lC_SseK\n","To: /content/Toronto_Collisions.csv\n","100%|██████████| 21.2M/21.2M [00:00<00:00, 132MB/s] \n"]},{"output_type":"execute_result","data":{"text/plain":["'Toronto_Collisions.csv'"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":2}],"source":["#Set viewing permission to 'Anyone with the link' if not already done\n","#File ID from the Google Drive link -> https://drive.google.com/file/d/FILE_ID/view?usp=sharing\n","file_id = '14KpYro56AbayWBQZ6CJfootZ-lC_SseK'\n","url = f'https://drive.google.com/uc?id={file_id}'\n","\n","#Download the file and save the name of the file\n","Toronto_Collisions = 'Toronto_Collisions.csv'\n","gdown.download(url, Toronto_Collisions, quiet=False)"]},{"cell_type":"code","execution_count":3,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":348},"executionInfo":{"elapsed":787,"status":"ok","timestamp":1733118047282,"user":{"displayName":"Karuna Adhikari","userId":"14765861351042505468"},"user_tz":300},"id":"W4tARmVIrrDO","outputId":"6295989e-32d4-4964-ccfc-fd72d7b4ef2e"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["     OCC_DATE OCC_MONTH    OCC_DOW  OCC_YEAR  OCC_HOUR  COLLISION_LONGITUDE  \\\n","0  2020-01-01   January  Wednesday      2020       6.0           -79.197483   \n","1  2020-01-01   January  Wednesday      2020       1.0           -79.550892   \n","2  2020-01-01   January  Wednesday      2020       5.0           -79.336669   \n","3  2020-01-01   January  Wednesday      2020       2.0           -79.393760   \n","4  2020-01-01   January  Wednesday      2020       4.0           -79.312104   \n","\n","   COLLISION_LATITUDE  INTERSECTION_ID INTERSECTION_CLASSIFICATION  \\\n","0           43.758945         13448608                       MNRSL   \n","1           43.677196         13462655                       MJRSL   \n","2           43.797327         13443799                       MNRSL   \n","3           43.642772         13467856                       MNRSL   \n","4           43.748833         13450356                       MNRSL   \n","\n","   RED_LIGHT_CAMERA  Temp (°C)  Rel Hum (%)  Precip. Amount (mm)  \\\n","0                 0       -0.6         73.0                  0.0   \n","1                 0       -0.1         70.0                  0.0   \n","2                 0       -0.5         72.0                  0.2   \n","3                 0       -0.1         67.0                  0.0   \n","4                 0       -0.7         75.0                  0.0   \n","\n","   Visibility (km)  Stn Press (kPa)  SPD_KM  NUM_TRAFFIC_SIGNALS  \n","0             16.1            98.99      40                  1.0  \n","1             16.1            98.84      60                  1.0  \n","2             16.1            98.96      40                  0.0  \n","3             16.1            98.87      60                  1.0  \n","4             16.1            98.96      60                  0.0  "],"text/html":["\n","  <div id=\"df-d861709d-d3f1-44b7-b0c5-8765532181f4\" class=\"colab-df-container\">\n","    <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>OCC_DATE</th>\n","      <th>OCC_MONTH</th>\n","      <th>OCC_DOW</th>\n","      <th>OCC_YEAR</th>\n","      <th>OCC_HOUR</th>\n","      <th>COLLISION_LONGITUDE</th>\n","      <th>COLLISION_LATITUDE</th>\n","      <th>INTERSECTION_ID</th>\n","      <th>INTERSECTION_CLASSIFICATION</th>\n","      <th>RED_LIGHT_CAMERA</th>\n","      <th>Temp (°C)</th>\n","      <th>Rel Hum (%)</th>\n","      <th>Precip. Amount (mm)</th>\n","      <th>Visibility (km)</th>\n","      <th>Stn Press (kPa)</th>\n","      <th>SPD_KM</th>\n","      <th>NUM_TRAFFIC_SIGNALS</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>2020-01-01</td>\n","      <td>January</td>\n","      <td>Wednesday</td>\n","      <td>2020</td>\n","      <td>6.0</td>\n","      <td>-79.197483</td>\n","      <td>43.758945</td>\n","      <td>13448608</td>\n","      <td>MNRSL</td>\n","      <td>0</td>\n","      <td>-0.6</td>\n","      <td>73.0</td>\n","      <td>0.0</td>\n","      <td>16.1</td>\n","      <td>98.99</td>\n","      <td>40</td>\n","      <td>1.0</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2020-01-01</td>\n","      <td>January</td>\n","      <td>Wednesday</td>\n","      <td>2020</td>\n","      <td>1.0</td>\n","      <td>-79.550892</td>\n","      <td>43.677196</td>\n","      <td>13462655</td>\n","      <td>MJRSL</td>\n","      <td>0</td>\n","      <td>-0.1</td>\n","      <td>70.0</td>\n","      <td>0.0</td>\n","      <td>16.1</td>\n","      <td>98.84</td>\n","      <td>60</td>\n","      <td>1.0</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2020-01-01</td>\n","      <td>January</td>\n","      <td>Wednesday</td>\n","      <td>2020</td>\n","      <td>5.0</td>\n","      <td>-79.336669</td>\n","      <td>43.797327</td>\n","      <td>13443799</td>\n","      <td>MNRSL</td>\n","      <td>0</td>\n","      <td>-0.5</td>\n","      <td>72.0</td>\n","      <td>0.2</td>\n","      <td>16.1</td>\n","      <td>98.96</td>\n","      <td>40</td>\n","      <td>0.0</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>2020-01-01</td>\n","      <td>January</td>\n","      <td>Wednesday</td>\n","      <td>2020</td>\n","      <td>2.0</td>\n","      <td>-79.393760</td>\n","      <td>43.642772</td>\n","      <td>13467856</td>\n","      <td>MNRSL</td>\n","      <td>0</td>\n","      <td>-0.1</td>\n","      <td>67.0</td>\n","      <td>0.0</td>\n","      <td>16.1</td>\n","      <td>98.87</td>\n","      <td>60</td>\n","      <td>1.0</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>2020-01-01</td>\n","      <td>January</td>\n","      <td>Wednesday</td>\n","      <td>2020</td>\n","      <td>4.0</td>\n","      <td>-79.312104</td>\n","      <td>43.748833</td>\n","      <td>13450356</td>\n","      <td>MNRSL</td>\n","      <td>0</td>\n","      <td>-0.7</td>\n","      <td>75.0</td>\n","      <td>0.0</td>\n","      <td>16.1</td>\n","      <td>98.96</td>\n","      <td>60</td>\n","      <td>0.0</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d861709d-d3f1-44b7-b0c5-8765532181f4')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-d861709d-d3f1-44b7-b0c5-8765532181f4 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-d861709d-d3f1-44b7-b0c5-8765532181f4');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-f7ba86ce-0608-4433-ae2e-b2f99607d423\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f7ba86ce-0608-4433-ae2e-b2f99607d423')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-f7ba86ce-0608-4433-ae2e-b2f99607d423 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"Toronto_Collisions_df"}},"metadata":{},"execution_count":3}],"source":["#Read CSV file\n","Toronto_Collisions_df = pd.read_csv(Toronto_Collisions)\n","Toronto_Collisions_df.head()"]},{"cell_type":"markdown","metadata":{"id":"eqX1krDUVBUv"},"source":["# FINAL KDE"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"RfmVzQ3BSe8i"},"outputs":[],"source":["import numpy as np\n","import pandas as pd\n","import matplotlib.pyplot as plt\n","from sklearn.neighbors import KernelDensity\n","from matplotlib.colors import LinearSegmentedColormap\n","\n","# Define the grid over the area\n","longitude_min, longitude_max = Toronto_Collisions_df['COLLISION_LONGITUDE'].min(), Toronto_Collisions_df['COLLISION_LONGITUDE'].max()\n","latitude_min, latitude_max = Toronto_Collisions_df['COLLISION_LATITUDE'].min(), Toronto_Collisions_df['COLLISION_LATITUDE'].max()\n","\n","# Generate a grid of points for the heatmap\n","grid_size = 200  # Adjust grid size for resolution\n","x_grid = np.linspace(longitude_min, longitude_max, grid_size)\n","y_grid = np.linspace(latitude_min, latitude_max, grid_size)\n","X, Y = np.meshgrid(x_grid, y_grid)\n","grid_coords = np.vstack([X.ravel(), Y.ravel()]).T  # Flatten the grid for input to KDE\n","\n","# Fit KDE model to the collision data\n","kde = KernelDensity(kernel='gaussian', bandwidth=0.01)  # Adjust bandwidth for smoothness\n","kde.fit(Toronto_Collisions_df[['COLLISION_LONGITUDE', 'COLLISION_LATITUDE']])\n","\n","# Evaluate KDE on the grid\n","log_density = kde.score_samples(grid_coords)\n","density = np.exp(log_density).reshape(X.shape)  # Reshape to grid\n","# Now, `density` is a 2D array representing the KDE values at each grid point.\n","\n","# Define a custom colormap: blue (low), green, yellow, orange, red (high)\n","colors = [\"white\", \"green\", \"yellow\", \"orange\", \"red\"]\n","cmap = LinearSegmentedColormap.from_list(\"custom_cmap\", colors)\n","\n","# Plot the KDE density map with the custom colormap\n","plt.imshow(density, extent=[longitude_min, longitude_max, latitude_min, latitude_max],\n","           origin='lower', cmap=cmap, alpha=0.7)\n","plt.colorbar(label='Collision Density')\n","plt.xlabel('Longitude')\n","plt.ylabel('Latitude')\n","plt.title('Toronto Collision Density Map (KDE)')\n","plt.show()\n","\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":381,"status":"ok","timestamp":1732159775390,"user":{"displayName":"May Akenzua","userId":"02226476697109792099"},"user_tz":300},"id":"ThC2f_2isV7N","outputId":"0b2054a8-15a3-40c9-dd15-8225faec3cd8"},"outputs":[{"name":"stdout","output_type":"stream","text":["[1.30528348e-12 4.69957536e-12 1.72414954e-11 ... 1.39772435e-05\n"," 8.77788376e-06 5.52934252e-06]\n"]}],"source":["# Get the KDE risk values as an array\n","kde_risk_values = density.ravel()\n","\n","# Print the KDE risk values\n","print(kde_risk_values)"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":143,"status":"ok","timestamp":1732159812476,"user":{"displayName":"May Akenzua","userId":"02226476697109792099"},"user_tz":300},"id":"E8hm4ET8xMmA","outputId":"8ab3e101-d082-4cf6-ae04-dfb90b99d120"},"outputs":[{"name":"stdout","output_type":"stream","text":["       longitude   latitude       risk\n","6296  -79.389742  43.627069  18.109920\n","6297  -79.387143  43.627069  18.590582\n","6298  -79.384544  43.627069  18.775930\n","6299  -79.381945  43.627069  18.564798\n","6300  -79.379346  43.627069  17.884807\n","...          ...        ...        ...\n","30955 -79.236400  43.788090  18.333246\n","31151 -79.246797  43.789399  17.884849\n","31152 -79.244198  43.789399  18.044456\n","31153 -79.241599  43.789399  18.178917\n","31154 -79.238999  43.789399  18.159458\n","\n","[4000 rows x 3 columns]\n"]}],"source":["\n","# Create a DataFrame to store the results\n","df_risk = pd.DataFrame({'longitude': X.ravel(), 'latitude': Y.ravel(), 'risk': kde_risk_values})\n","\n","# Define a threshold to identify high-risk areas (adjust as needed)\n","risk_threshold = np.percentile(kde_risk_values, 90)  # Top 10%\n","\n","# Filter for high-risk areas\n","high_risk_areas = df_risk[df_risk['risk'] >= risk_threshold]\n","\n","# Print or visualize high-risk areas\n","print(high_risk_areas)"]},{"cell_type":"markdown","source":["FINAL KDE PREDICTION MODEL"],"metadata":{"id":"ghypTGFO_iaU"}},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":80},"executionInfo":{"elapsed":144,"status":"ok","timestamp":1732566845291,"user":{"displayName":"May Akenzua","userId":"02226476697109792099"},"user_tz":300},"id":"Xgq_NM897YXv","outputId":"7652c4e2-28d3-407b-9d09-a31d0f570959"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["KernelDensity(bandwidth=0.02)"],"text/html":["<style>#sk-container-id-1 {\n","  /* Definition of color scheme common for light and dark mode */\n","  --sklearn-color-text: black;\n","  --sklearn-color-line: gray;\n","  /* Definition of color scheme for unfitted estimators */\n","  --sklearn-color-unfitted-level-0: #fff5e6;\n","  --sklearn-color-unfitted-level-1: #f6e4d2;\n","  --sklearn-color-unfitted-level-2: #ffe0b3;\n","  --sklearn-color-unfitted-level-3: chocolate;\n","  /* Definition of color scheme for fitted estimators */\n","  --sklearn-color-fitted-level-0: #f0f8ff;\n","  --sklearn-color-fitted-level-1: #d4ebff;\n","  --sklearn-color-fitted-level-2: #b3dbfd;\n","  --sklearn-color-fitted-level-3: cornflowerblue;\n","\n","  /* Specific color for light theme */\n","  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n","  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n","  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n","  --sklearn-color-icon: #696969;\n","\n","  @media (prefers-color-scheme: dark) {\n","    /* Redefinition of color scheme for dark theme */\n","    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n","    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n","    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n","    --sklearn-color-icon: #878787;\n","  }\n","}\n","\n","#sk-container-id-1 {\n","  color: var(--sklearn-color-text);\n","}\n","\n","#sk-container-id-1 pre {\n","  padding: 0;\n","}\n","\n","#sk-container-id-1 input.sk-hidden--visually {\n","  border: 0;\n","  clip: rect(1px 1px 1px 1px);\n","  clip: rect(1px, 1px, 1px, 1px);\n","  height: 1px;\n","  margin: -1px;\n","  overflow: hidden;\n","  padding: 0;\n","  position: absolute;\n","  width: 1px;\n","}\n","\n","#sk-container-id-1 div.sk-dashed-wrapped {\n","  border: 1px dashed var(--sklearn-color-line);\n","  margin: 0 0.4em 0.5em 0.4em;\n","  box-sizing: border-box;\n","  padding-bottom: 0.4em;\n","  background-color: var(--sklearn-color-background);\n","}\n","\n","#sk-container-id-1 div.sk-container {\n","  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n","     but bootstrap.min.css set `[hidden] { display: none !important; }`\n","     so we also need the `!important` here to be able to override the\n","     default hidden behavior on the sphinx rendered scikit-learn.org.\n","     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n","  display: inline-block !important;\n","  position: relative;\n","}\n","\n","#sk-container-id-1 div.sk-text-repr-fallback {\n","  display: none;\n","}\n","\n","div.sk-parallel-item,\n","div.sk-serial,\n","div.sk-item {\n","  /* draw centered vertical line to link estimators */\n","  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n","  background-size: 2px 100%;\n","  background-repeat: no-repeat;\n","  background-position: center center;\n","}\n","\n","/* Parallel-specific style estimator block */\n","\n","#sk-container-id-1 div.sk-parallel-item::after {\n","  content: \"\";\n","  width: 100%;\n","  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n","  flex-grow: 1;\n","}\n","\n","#sk-container-id-1 div.sk-parallel {\n","  display: flex;\n","  align-items: stretch;\n","  justify-content: center;\n","  background-color: var(--sklearn-color-background);\n","  position: relative;\n","}\n","\n","#sk-container-id-1 div.sk-parallel-item {\n","  display: flex;\n","  flex-direction: column;\n","}\n","\n","#sk-container-id-1 div.sk-parallel-item:first-child::after {\n","  align-self: flex-end;\n","  width: 50%;\n","}\n","\n","#sk-container-id-1 div.sk-parallel-item:last-child::after {\n","  align-self: flex-start;\n","  width: 50%;\n","}\n","\n","#sk-container-id-1 div.sk-parallel-item:only-child::after {\n","  width: 0;\n","}\n","\n","/* Serial-specific style estimator block */\n","\n","#sk-container-id-1 div.sk-serial {\n","  display: flex;\n","  flex-direction: column;\n","  align-items: center;\n","  background-color: var(--sklearn-color-background);\n","  padding-right: 1em;\n","  padding-left: 1em;\n","}\n","\n","\n","/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n","clickable and can be expanded/collapsed.\n","- Pipeline and ColumnTransformer use this feature and define the default style\n","- Estimators will overwrite some part of the style using the `sk-estimator` class\n","*/\n","\n","/* Pipeline and ColumnTransformer style (default) */\n","\n","#sk-container-id-1 div.sk-toggleable {\n","  /* Default theme specific background. It is overwritten whether we have a\n","  specific estimator or a Pipeline/ColumnTransformer */\n","  background-color: var(--sklearn-color-background);\n","}\n","\n","/* Toggleable label */\n","#sk-container-id-1 label.sk-toggleable__label {\n","  cursor: pointer;\n","  display: block;\n","  width: 100%;\n","  margin-bottom: 0;\n","  padding: 0.5em;\n","  box-sizing: border-box;\n","  text-align: center;\n","}\n","\n","#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n","  /* Arrow on the left of the label */\n","  content: \"▸\";\n","  float: left;\n","  margin-right: 0.25em;\n","  color: var(--sklearn-color-icon);\n","}\n","\n","#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n","  color: var(--sklearn-color-text);\n","}\n","\n","/* Toggleable content - dropdown */\n","\n","#sk-container-id-1 div.sk-toggleable__content {\n","  max-height: 0;\n","  max-width: 0;\n","  overflow: hidden;\n","  text-align: left;\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-0);\n","}\n","\n","#sk-container-id-1 div.sk-toggleable__content.fitted {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-0);\n","}\n","\n","#sk-container-id-1 div.sk-toggleable__content pre {\n","  margin: 0.2em;\n","  border-radius: 0.25em;\n","  color: var(--sklearn-color-text);\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-0);\n","}\n","\n","#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n","  /* unfitted */\n","  background-color: var(--sklearn-color-fitted-level-0);\n","}\n","\n","#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n","  /* Expand drop-down */\n","  max-height: 200px;\n","  max-width: 100%;\n","  overflow: auto;\n","}\n","\n","#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n","  content: \"▾\";\n","}\n","\n","/* Pipeline/ColumnTransformer-specific style */\n","\n","#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n","  color: var(--sklearn-color-text);\n","  background-color: var(--sklearn-color-unfitted-level-2);\n","}\n","\n","#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n","  background-color: var(--sklearn-color-fitted-level-2);\n","}\n","\n","/* Estimator-specific style */\n","\n","/* Colorize estimator box */\n","#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-2);\n","}\n","\n","#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-2);\n","}\n","\n","#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n","#sk-container-id-1 div.sk-label label {\n","  /* The background is the default theme color */\n","  color: var(--sklearn-color-text-on-default-background);\n","}\n","\n","/* On hover, darken the color of the background */\n","#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n","  color: var(--sklearn-color-text);\n","  background-color: var(--sklearn-color-unfitted-level-2);\n","}\n","\n","/* Label box, darken color on hover, fitted */\n","#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n","  color: var(--sklearn-color-text);\n","  background-color: var(--sklearn-color-fitted-level-2);\n","}\n","\n","/* Estimator label */\n","\n","#sk-container-id-1 div.sk-label label {\n","  font-family: monospace;\n","  font-weight: bold;\n","  display: inline-block;\n","  line-height: 1.2em;\n","}\n","\n","#sk-container-id-1 div.sk-label-container {\n","  text-align: center;\n","}\n","\n","/* Estimator-specific */\n","#sk-container-id-1 div.sk-estimator {\n","  font-family: monospace;\n","  border: 1px dotted var(--sklearn-color-border-box);\n","  border-radius: 0.25em;\n","  box-sizing: border-box;\n","  margin-bottom: 0.5em;\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-0);\n","}\n","\n","#sk-container-id-1 div.sk-estimator.fitted {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-0);\n","}\n","\n","/* on hover */\n","#sk-container-id-1 div.sk-estimator:hover {\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-2);\n","}\n","\n","#sk-container-id-1 div.sk-estimator.fitted:hover {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-2);\n","}\n","\n","/* Specification for estimator info (e.g. \"i\" and \"?\") */\n","\n","/* Common style for \"i\" and \"?\" */\n","\n",".sk-estimator-doc-link,\n","a:link.sk-estimator-doc-link,\n","a:visited.sk-estimator-doc-link {\n","  float: right;\n","  font-size: smaller;\n","  line-height: 1em;\n","  font-family: monospace;\n","  background-color: var(--sklearn-color-background);\n","  border-radius: 1em;\n","  height: 1em;\n","  width: 1em;\n","  text-decoration: none !important;\n","  margin-left: 1ex;\n","  /* unfitted */\n","  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n","  color: var(--sklearn-color-unfitted-level-1);\n","}\n","\n",".sk-estimator-doc-link.fitted,\n","a:link.sk-estimator-doc-link.fitted,\n","a:visited.sk-estimator-doc-link.fitted {\n","  /* fitted */\n","  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n","  color: var(--sklearn-color-fitted-level-1);\n","}\n","\n","/* On hover */\n","div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",".sk-estimator-doc-link:hover,\n","div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",".sk-estimator-doc-link:hover {\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-3);\n","  color: var(--sklearn-color-background);\n","  text-decoration: none;\n","}\n","\n","div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",".sk-estimator-doc-link.fitted:hover,\n","div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",".sk-estimator-doc-link.fitted:hover {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-3);\n","  color: var(--sklearn-color-background);\n","  text-decoration: none;\n","}\n","\n","/* Span, style for the box shown on hovering the info icon */\n",".sk-estimator-doc-link span {\n","  display: none;\n","  z-index: 9999;\n","  position: relative;\n","  font-weight: normal;\n","  right: .2ex;\n","  padding: .5ex;\n","  margin: .5ex;\n","  width: min-content;\n","  min-width: 20ex;\n","  max-width: 50ex;\n","  color: var(--sklearn-color-text);\n","  box-shadow: 2pt 2pt 4pt #999;\n","  /* unfitted */\n","  background: var(--sklearn-color-unfitted-level-0);\n","  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n","}\n","\n",".sk-estimator-doc-link.fitted span {\n","  /* fitted */\n","  background: var(--sklearn-color-fitted-level-0);\n","  border: var(--sklearn-color-fitted-level-3);\n","}\n","\n",".sk-estimator-doc-link:hover span {\n","  display: block;\n","}\n","\n","/* \"?\"-specific style due to the `<a>` HTML tag */\n","\n","#sk-container-id-1 a.estimator_doc_link {\n","  float: right;\n","  font-size: 1rem;\n","  line-height: 1em;\n","  font-family: monospace;\n","  background-color: var(--sklearn-color-background);\n","  border-radius: 1rem;\n","  height: 1rem;\n","  width: 1rem;\n","  text-decoration: none;\n","  /* unfitted */\n","  color: var(--sklearn-color-unfitted-level-1);\n","  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n","}\n","\n","#sk-container-id-1 a.estimator_doc_link.fitted {\n","  /* fitted */\n","  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n","  color: var(--sklearn-color-fitted-level-1);\n","}\n","\n","/* On hover */\n","#sk-container-id-1 a.estimator_doc_link:hover {\n","  /* unfitted */\n","  background-color: var(--sklearn-color-unfitted-level-3);\n","  color: var(--sklearn-color-background);\n","  text-decoration: none;\n","}\n","\n","#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n","  /* fitted */\n","  background-color: var(--sklearn-color-fitted-level-3);\n","}\n","</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KernelDensity(bandwidth=0.02)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;KernelDensity<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.neighbors.KernelDensity.html\">?<span>Documentation for KernelDensity</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>KernelDensity(bandwidth=0.02)</pre></div> </div></div></div></div>"]},"metadata":{},"execution_count":4}],"source":["import pandas as pd\n","import numpy as np\n","from sklearn.model_selection import train_test_split\n","from sklearn.neighbors import KernelDensity\n","\n","# Extract longitude and latitude\n","X = Toronto_Collisions_df[['COLLISION_LONGITUDE', 'COLLISION_LATITUDE']].values\n","\n","# Split the data into training and testing sets\n","X_train, X_test = train_test_split(X, test_size=0.2, random_state=42)\n","\n","# Train the KDE model on the training data\n","kde = KernelDensity(kernel='gaussian', bandwidth=0.02)  # Adjust bandwidth as needed\n","kde.fit(X_train)"]},{"cell_type":"code","source":["import pickle\n","import pandas as pd\n","import numpy as np\n","from sklearn.model_selection import train_test_split\n","from sklearn.neighbors import KernelDensity\n","\n","# Extract longitude and latitude\n","X = Toronto_Collisions_df[['COLLISION_LONGITUDE', 'COLLISION_LATITUDE']].values\n","\n","# Split the data into training and testing sets\n","X_train, X_test = train_test_split(X, test_size=0.2, random_state=42)\n","\n","'''\n","# Fit the model on training set\n","kde_model = KernelDensity(kernel='gaussian', bandwidth=0.02)  # Adjust bandwidth as needed\n","kde_model.fit(X_train)\n","# save the model to disk\n","filename = 'kde.sav'\n","pickle.dump(kde_model, open(filename, 'wb'))\n","'''"],"metadata":{"id":"86apL3Fc8RgM","colab":{"base_uri":"https://localhost:8080/","height":52},"executionInfo":{"status":"ok","timestamp":1733118047283,"user_tz":300,"elapsed":30,"user":{"displayName":"Karuna Adhikari","userId":"14765861351042505468"}},"outputId":"cdeb5676-4e3b-440a-d15e-486806512ce4"},"execution_count":4,"outputs":[{"output_type":"execute_result","data":{"text/plain":["\"\\n# Fit the model on training set\\nkde_model = KernelDensity(kernel='gaussian', bandwidth=0.02)  # Adjust bandwidth as needed\\nkde_model.fit(X_train)\\n# save the model to disk\\nfilename = 'kde.sav'\\npickle.dump(kde_model, open(filename, 'wb'))\\n\""],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":4}]},{"cell_type":"code","execution_count":null,"metadata":{"id":"O98KQZPA7-JX"},"outputs":[],"source":["'''# Function to create coordinate arrays from data points\n","def get_coordinate_array(data):\n","\n","  coordinates = []\n","  for point in data:\n","    coordinates.append(list(point))\n","  return np.array(coordinates)\n","\n","# Create coordinate arrays for training and testing sets (if needed)\n","train_coords_array = get_coordinate_array(X_train)\n","test_coords_array = get_coordinate_array(X_test)\n","\n","# Calculate KDE risks for training and testing sets\n","train_risks = kde.score_samples(train_coords_array)\n","test_risks = kde.score_samples(test_coords_array)\n","\n","\n","print(\"KDE risks for the training set:\", np.exp(train_risks))  # Print actual density values\n","print(\"KDE risks for the testing set:\", np.exp(test_risks))\n","'''"]},{"cell_type":"code","source":["kde.fit(X_train)\n","\n","density = kde.score_samples(X_test)\n","\n","'''\n","# Define a custom colormap: blue (low), green, yellow, orange, red (high)\n","colors = [\"white\", \"green\", \"yellow\", \"orange\", \"red\"]\n","cmap = LinearSegmentedColormap.from_list(\"custom_cmap\", colors)\n","\n","# Plot the KDE density map with the custom colormap\n","plt.imshow(density, extent=[longitude_min, longitude_max, latitude_min, latitude_max],\n","           origin='lower', cmap=cmap, alpha=0.7)\n","plt.colorbar(label='Collision Density')\n","plt.xlabel('Longitude')\n","plt.ylabel('Latitude')\n","plt.title('Toronto Collision Density Map (KDE)')\n","plt.show()\n","'''\n"],"metadata":{"id":"IeI8JUTWv0Sm"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# CV For Bandwidth"],"metadata":{"id":"uimTe_Ji3qix"}},{"cell_type":"code","source":["import numpy as np\n","import pandas as pd\n","import matplotlib.pyplot as plt\n","from sklearn.model_selection import GridSearchCV\n","from sklearn.neighbors import KernelDensity\n","\n","bandwidths = 10 ** np.linspace(-1, 1, 100)\n","\n","grid = GridSearchCV(KernelDensity(kernel='gaussian'),\n","                    {'bandwidth': bandwidths},\n","                    cv=100)\n","\n","grid.fit(X_train);\n","\n","grid.best_params_"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":211},"id":"eRZEvOcx3uw1","executionInfo":{"status":"error","timestamp":1733121902161,"user_tz":300,"elapsed":2327,"user":{"displayName":"Karuna Adhikari","userId":"14765861351042505468"}},"outputId":"dccbb923-9d16-4b1b-83b7-7cf3092e36a4"},"execution_count":1,"outputs":[{"output_type":"error","ename":"NameError","evalue":"name 'X_train' is not defined","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m<ipython-input-1-874075f207d0>\u001b[0m in \u001b[0;36m<cell line: 13>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     11\u001b[0m                     cv=100)\n\u001b[1;32m     12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m \u001b[0mgrid\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m;\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0mgrid\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbest_params_\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mNameError\u001b[0m: name 'X_train' is not defined"]}]},{"cell_type":"code","source":[],"metadata":{"id":"I1Ct3VZI4nni"},"execution_count":null,"outputs":[]}],"metadata":{"colab":{"provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"name":"python"}},"nbformat":4,"nbformat_minor":0}