Add project files

UM_projekt.ipynb

@@ -0,0 +1,190 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.7.1"
+    },
+    "colab": {
+      "name": "UM_projekt.ipynb",
+      "provenance": []
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "CyNKlKu4mVOD",
+        "outputId": "b3f1fe30-a641-4d4e-872d-833739924713"
+      },
+      "source": [
+        "import pandas as pd\n",
+        "import seaborn as sns\n",
+        "import datetime\n",
+        "import matplotlib.pyplot as plt\n",
+        "from sklearn.metrics import mean_squared_error\n",
+        "\n",
+        "netflix=pd.read_csv('netflix_titles_enriched.csv')\n",
+        "\n",
+        "netflix_cleaned = netflix[netflix.rottentomatoes_audience_score > 0].sort_values(by = 'rottentomatoes_audience_score')\n",
+        "netflix_cleaned.rottentomatoes_audience_score /= 100\n",
+        "netflix_cleaned.drop(['rottentomatoes_audience_#reviews',\n",
+        "       'rottentomatoes_audience_review', 'rottentomatoes_tomatometer_score',\n",
+        "       'rottentomatoes_critics_#reviews', 'rottentomatoes_critic_review'], axis = 1)\n",
+        "\n",
+        "netflix_cleaned.date_added = netflix_cleaned.date_added.dropna().apply(lambda x: datetime.datetime.strptime(x[1:] if x[0] == ' ' else x, '%B %d, %Y'))\n",
+        "\n",
+        "netflix_cleaned.update(netflix_cleaned.select_dtypes(include = 'object').apply(lambda col: col.str.lower()))\n",
+        "\n",
+        "\n",
+        "\n",
+        "movies = netflix_cleaned[netflix_cleaned.type == 'movie']\n",
+        "\n",
+        "\n",
+        "movies.duration = movies.duration.str.extract(r'(\\d*)( min)')[0].astype('int32')\n",
+        "\n",
+        "from sklearn.preprocessing import MultiLabelBinarizer\n",
+        "mlb = MultiLabelBinarizer()\n",
+        "\n",
+        "movies = movies.join(pd.DataFrame(mlb.fit_transform(movies.pop('listed_in').str.split(', ')),\n",
+        "                          columns=mlb.classes_,\n",
+        "                          index=movies.index))\n",
+        "movies.drop(['movies'], axis = 1)\n",
+        "\n",
+        "movies = movies[['release_year', 'duration',\n",
+        "       'rottentomatoes_audience_score',\n",
+        "       'action & adventure', 'anime features', 'children & family movies',\n",
+        "       'classic movies', 'comedies', 'cult movies', 'documentaries', 'dramas',\n",
+        "       'faith & spirituality', 'horror movies', 'independent movies',\n",
+        "       'international movies', 'lgbtq movies', 'movies', 'music & musicals',\n",
+        "       'romantic movies', 'sci-fi & fantasy', 'sports movies',\n",
+        "       'stand-up comedy', 'thrillers']]\n",
+        "\n",
+        "import sklearn\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "movies_train, movies_test = sklearn.model_selection.train_test_split(movies,test_size=0.20, random_state=42)\n",
+        "#movies_test, movies_val = sklearn.model_selection.train_test_split(movies_test,test_size=0.50, random_state=42)\n",
+        "\n",
+        "\n",
+        "x_train = movies_train.copy()\n",
+        "y_train = x_train.pop('rottentomatoes_audience_score')\n",
+        "#x_train.pop('Unnamed: 0')\n",
+        "\n",
+        "x_test = movies_test.copy()\n",
+        "y_test = x_test.pop('rottentomatoes_audience_score')\n",
+        "#y_test.pop('Unnamed: 0')\n"
+      ],
+      "execution_count": 60,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "2700\n",
+            "2160 540\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "stream",
+          "text": [
+            "/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py:5170: SettingWithCopyWarning: \n",
+            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+            "Try using .loc[row_indexer,col_indexer] = value instead\n",
+            "\n",
+            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+            "  self[name] = value\n"
+          ],
+          "name": "stderr"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "MqmpAk48n-LR"
+      },
+      "source": [
+        "from sklearn.linear_model import SGDRegressor\n",
+        "from sklearn.pipeline import make_pipeline\n",
+        "from sklearn.preprocessing import StandardScaler\n",
+        "modelSGD = make_pipeline(StandardScaler(), SGDRegressor())\n",
+        "modelSGD.fit(x_train, y_train) \n",
+        "y_predicted = modelSGD.predict(x_val)\n",
+        "errorSGD = mean_squared_error(y_val, y_predicted)"
+      ],
+      "execution_count": 61,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "WLzrNTM7lxnE"
+      },
+      "source": [
+        "from sklearn.linear_model import LinearRegression\n",
+        "modelLR = make_pipeline(StandardScaler(), LinearRegression())\n",
+        "modelLR.fit(x_train, y_train) \n",
+        "y_predicted = modelLR.predict(x_val)\n",
+        "errorLR = mean_squared_error(y_val, y_predicted)"
+      ],
+      "execution_count": 62,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "x4C2ExxamxU5"
+      },
+      "source": [
+        "from sklearn.svm import SVR\n",
+        "modelSVR = make_pipeline(StandardScaler(), SVR())\n",
+        "modelSVR.fit(x_train, y_train) \n",
+        "y_predicted = modelSVR.predict(x_val)\n",
+        "errorSVR = mean_squared_error(y_val, y_predicted)"
+      ],
+      "execution_count": 63,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "TNj0zacwroWJ",
+        "outputId": "12378b41-418d-464f-a77f-8455af754953"
+      },
+      "source": [
+        "print(errorLR, errorSGD, errorSVR)"
+      ],
+      "execution_count": 64,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "0.040133803263361176 0.040076924018007165 0.04124993242855958\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    }
+  ]
+}