Created using Colaboratory

FnV_Experiment.ipynb

@@ -0,0 +1,453 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "FnV - Experiment.ipynb",
+      "provenance": [],
+      "authorship_tag": "ABX9TyP3QrLYzuRpaXcYfFN083H1",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/patal-dev/april/blob/main/FnV_Experiment.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "%matplotlib inline\n",
+        "\n",
+        "import logging\n",
+        "logging.getLogger('googleapiclient.discovery_cache').setLevel(logging.ERROR)\n",
+        "\n",
+        "# Code to read csv file into Colaboratory:\n",
+        "!pip install -U -q PyDrive\n",
+        "from pydrive.auth import GoogleAuth\n",
+        "from pydrive.drive import GoogleDrive\n",
+        "from google.colab import auth\n",
+        "from oauth2client.client import GoogleCredentials\n",
+        "# Authenticate and create the PyDrive client.\n",
+        "auth.authenticate_user()\n",
+        "gauth = GoogleAuth()\n",
+        "gauth.credentials = GoogleCredentials.get_application_default()\n",
+        "drive = GoogleDrive(gauth)\n",
+        "link = 'https://drive.google.com/open?id=1XcFFQS1ZoUOPs9vSJcA_o-Z1rvxi1Kod'\n",
+        "fluff, id = link.split('=')\n",
+        "\n",
+        "downloaded = drive.CreateFile({'id':id}) \n",
+        "downloaded.GetContentFile('wiki.mat')"
+      ],
+      "metadata": {
+        "id": "zmziIdpUPjS2"
+      },
+      "execution_count": 24,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Data\n",
+        "\n",
+        "\n",
+        "\n",
+        "*   dob: date of birth (Matlab serial date number)\n",
+        "*photo_taken: year when the photo was taken\n",
+        "*full_path: path to file\n",
+        "*gender: 0 for female and 1 for male, NaN if unknown\n",
+        "*name: name of the celebrity\n",
+        "*face_location: location of the face. \n",
+        "*face_score: detector score (the higher the better). Inf implies that no face was found in the image and the face_location then just returns the entire image\n",
+        "*second_face_score: detector score of the face with the second highest score. This is useful to ignore images with more than one face. second_face_score is NaN if no second face was detected.\n",
+        "*celeb_names (IMDB only): list of all celebrity names\n",
+        "*celeb_id (IMDB only): index of celebrity name\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "Cad-POdXV7kC"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 57,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "N8p-PTdI34e4",
+        "outputId": "e5290e36-00e0-48e9-ed7d-fb5b9d5dfec0"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "name 62204\n",
+            "[['723671.0' '703186.0' '711677.0' ... '720620.0' '723893.0' '713846.0']\n",
+            " ['2009.0' '1964.0' '2008.0' ... '2013.0' '2011.0' '2008.0']\n",
+            " ['17/10000217_1981-05-05_2009.jpg' '48/10000548_1925-04-04_1964.jpg'\n",
+            "  '12/100012_1948-07-03_2008.jpg' ... '09/9998109_1972-12-27_2013.jpg'\n",
+            "  '00/9999400_1981-12-13_2011.jpg' '80/999980_1954-06-11_2008.jpg']\n",
+            " ...\n",
+            " ['1.0' '1.0' '1.0' ... '1.0' '1.0' '0.0']\n",
+            " ['4.3009623883308095' '2.6456394971903463' '4.329328832406529' ...\n",
+            "  '3.4943031690208564' '-inf' '5.486916546849864']\n",
+            " ['nan' '1.9492479052091165' 'nan' ... 'nan' 'nan' 'nan']]\n"
+          ]
+        }
+      ],
+      "source": [
+        "import scipy.io\n",
+        "import numpy as np\n",
+        "\n",
+        "mat = scipy.io.loadmat('wiki.mat')\n",
+        "fields = ('dob', 'photo_taken', 'full_path', 'gender', 'name', \n",
+        "          'face_location', 'face_score', 'second_face_score')\n",
+        "\n",
+        "l = 62328\n",
+        "data = np.empty((0, l))\n",
+        "# data = np.array([])\n",
+        "for i, field in enumerate(fields):\n",
+        "  if field == 'face_location':\n",
+        "    data = np.append(data, [np.empty(l)], axis=0)\n",
+        "    continue\n",
+        "  values = np.hstack(mat['wiki'][0][0][i].flatten())\n",
+        "  if len(values) < l:\n",
+        "    print(field, len(values))\n",
+        "    remainder = np.empty(l - len(values))\n",
+        "    values = np.concatenate((values, remainder))\n",
+        "  data = np.append(data, [values], axis=0)\n",
+        "\n",
+        "print(data)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "print(data.shape)\n",
+        "df = pd.DataFrame(data).transpose()\n",
+        "df.columns = fields\n",
+        "\n",
+        "df"
+      ],
+      "metadata": {
+        "id": "sW4oRDTs4L4p",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 441
+        },
+        "outputId": "9dfa7921-f09d-4c20-832e-1d0774ae19f6"
+      },
+      "execution_count": 58,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "(8, 62328)\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "            dob photo_taken                        full_path gender  \\\n",
+              "0      723671.0      2009.0  17/10000217_1981-05-05_2009.jpg    1.0   \n",
+              "1      703186.0      1964.0  48/10000548_1925-04-04_1964.jpg    1.0   \n",
+              "2      711677.0      2008.0    12/100012_1948-07-03_2008.jpg    1.0   \n",
+              "3      705061.0      1961.0  65/10001965_1930-05-23_1961.jpg    1.0   \n",
+              "4      720044.0      2012.0  16/10002116_1971-05-31_2012.jpg    0.0   \n",
+              "...         ...         ...                              ...    ...   \n",
+              "62323  707582.0      1963.0   49/9996949_1937-04-17_1963.jpg    1.0   \n",
+              "62324  711338.0      1970.0   32/9997032_1947-07-30_1970.jpg    1.0   \n",
+              "62325  720620.0      2013.0   09/9998109_1972-12-27_2013.jpg    1.0   \n",
+              "62326  723893.0      2011.0   00/9999400_1981-12-13_2011.jpg    1.0   \n",
+              "62327  713846.0      2008.0    80/999980_1954-06-11_2008.jpg    0.0   \n",
+              "\n",
+              "                        name face_location          face_score  \\\n",
+              "0            Sami Jauhojärvi           1.0  4.3009623883308095   \n",
+              "1             Dettmar Cramer           1.0  2.6456394971903463   \n",
+              "2                Marc Okrand           1.0   4.329328832406529   \n",
+              "3       Aleksandar Matanović           1.0                -inf   \n",
+              "4               Diana Damrau           0.0   3.408442415222501   \n",
+              "...                      ...           ...                 ...   \n",
+              "62323                    0.0           1.0   4.029267756985114   \n",
+              "62324                    0.0           1.0                -inf   \n",
+              "62325  4.68486041878186e-310           1.0  3.4943031690208564   \n",
+              "62326  4.68486041878186e-310           1.0                -inf   \n",
+              "62327  6.92474272034567e-310           0.0   5.486916546849864   \n",
+              "\n",
+              "        second_face_score  \n",
+              "0                     nan  \n",
+              "1      1.9492479052091165  \n",
+              "2                     nan  \n",
+              "3                     nan  \n",
+              "4                     nan  \n",
+              "...                   ...  \n",
+              "62323                 nan  \n",
+              "62324                 nan  \n",
+              "62325                 nan  \n",
+              "62326                 nan  \n",
+              "62327                 nan  \n",
+              "\n",
+              "[62328 rows x 8 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-bba92cb7-f4b3-4205-94cc-5753d33495c5\">\n",
+              "    <div 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>dob</th>\n",
+              "      <th>photo_taken</th>\n",
+              "      <th>full_path</th>\n",
+              "      <th>gender</th>\n",
+              "      <th>name</th>\n",
+              "      <th>face_location</th>\n",
+              "      <th>face_score</th>\n",
+              "      <th>second_face_score</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>723671.0</td>\n",
+              "      <td>2009.0</td>\n",
+              "      <td>17/10000217_1981-05-05_2009.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>Sami Jauhojärvi</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>4.3009623883308095</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>703186.0</td>\n",
+              "      <td>1964.0</td>\n",
+              "      <td>48/10000548_1925-04-04_1964.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>Dettmar Cramer</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>2.6456394971903463</td>\n",
+              "      <td>1.9492479052091165</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>711677.0</td>\n",
+              "      <td>2008.0</td>\n",
+              "      <td>12/100012_1948-07-03_2008.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>Marc Okrand</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>4.329328832406529</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>705061.0</td>\n",
+              "      <td>1961.0</td>\n",
+              "      <td>65/10001965_1930-05-23_1961.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>Aleksandar Matanović</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>-inf</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>720044.0</td>\n",
+              "      <td>2012.0</td>\n",
+              "      <td>16/10002116_1971-05-31_2012.jpg</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>Diana Damrau</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>3.408442415222501</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>62323</th>\n",
+              "      <td>707582.0</td>\n",
+              "      <td>1963.0</td>\n",
+              "      <td>49/9996949_1937-04-17_1963.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>4.029267756985114</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>62324</th>\n",
+              "      <td>711338.0</td>\n",
+              "      <td>1970.0</td>\n",
+              "      <td>32/9997032_1947-07-30_1970.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>-inf</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>62325</th>\n",
+              "      <td>720620.0</td>\n",
+              "      <td>2013.0</td>\n",
+              "      <td>09/9998109_1972-12-27_2013.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>4.68486041878186e-310</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>3.4943031690208564</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>62326</th>\n",
+              "      <td>723893.0</td>\n",
+              "      <td>2011.0</td>\n",
+              "      <td>00/9999400_1981-12-13_2011.jpg</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>4.68486041878186e-310</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>-inf</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>62327</th>\n",
+              "      <td>713846.0</td>\n",
+              "      <td>2008.0</td>\n",
+              "      <td>80/999980_1954-06-11_2008.jpg</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>6.92474272034567e-310</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>5.486916546849864</td>\n",
+              "      <td>nan</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>62328 rows × 8 columns</p>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bba92cb7-f4b3-4205-94cc-5753d33495c5')\"\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 0 24 24\"\n",
+              "       width=\"24px\">\n",
+              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
+              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
+              "  </svg>\n",
+              "      </button>\n",
+              "      \n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      flex-wrap:wrap;\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",
+              "    [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-bba92cb7-f4b3-4205-94cc-5753d33495c5 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-bba92cb7-f4b3-4205-94cc-5753d33495c5');\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",
+              "  </div>\n",
+              "  "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 58
+        }
+      ]
+    }
+  ]
+}