{ "cells": [ { "cell_type": "code", "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report\n", "\n", "# Wczytanie danych\n", "df = pd.read_csv('Pokemon.csv')\n", "\n", "# Wybór cech i etykiet\n", "X = df[['Attack', 'Defense']]\n", "Y = df['Legendary'].astype(int) # Konwersja wartości logicznych na liczby\n", "print(f\"Liczba zwykłych Pokémonów (0): {Y.value_counts()[0]}\")\n", "print(f\"Liczba legendarnych Pokémonów (1): {Y.value_counts()[1]}\")\n", "# Podział na zbiór uczący i testowy\n", "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)\n", "\n", "# Tworzenie i trenowanie modelu\n", "model = LogisticRegression()\n", "model.fit(X_train, Y_train)\n", "\n", "# Predykcja na zbiorze testowym\n", "Y_pred = model.predict(X_test)\n", "\n", "# Ocena skuteczności\n", "accuracy = accuracy_score(Y_test, Y_pred)\n", "precision = precision_score(Y_test, Y_pred)\n", "recall = recall_score(Y_test, Y_pred)\n", "f1 = f1_score(Y_test, Y_pred)\n", "\n", "# Wyświetlenie metryk\n", "print(f'Accuracy: {accuracy:.4f}')\n", "print(f'Precision: {precision:.4f}')\n", "print(f'Recall: {recall:.4f}')\n", "print(f'F1-score: {f1:.4f}')\n", "print('\\nClassification Report:\\n', classification_report(Y_test, Y_pred))\n", "\n", "# Wizualizacja danych i decyzji\n", "plt.figure(figsize=(8, 6))\n", "plt.scatter(X_test['Attack'], X_test['Defense'], c=Y_pred, cmap='coolwarm', edgecolors='k', alpha=0.7)\n", "plt.xlabel('Attack')\n", "plt.ylabel('Defense')\n", "plt.title('Klasyfikacja Pokémonów (legendarny vs. zwykły)')\n", "plt.colorbar(label='Legenda: 0 - zwykły, 1 - legendarny')\n", "plt.show()\n" ], "metadata": { "id": "j5fjxVBZPpF9" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Sekcja 1: Import bibliotek\n", "import pandas as pd\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from scipy import stats\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n", "import numpy as np" ], "metadata": { "id": "vSFTkPj1-TK4" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Sekcja 2: Wczytanie i zapoznanie z danymi\n", "\n", "#Wczytanie zbioru “Titanic” z biblioteki seaborn\n", "df = sns.load_dataset(\"titanic\")\n", "\n", "# Wyświetlenie pierwszych 10 wierszy danych\n", "print(df.head(10))\n", "\n", "print(\"\\nLiczba brakujących wartości przed czyszczeniem:\")\n", "print(df.isnull().sum())\n", "\n", "\n", "# Usunięcie rekordów z brakującą daną w poli 'age' i wyświetlenie danych o liczbie wierszy\n", "df = df.dropna(subset=['age'])\n", "\n", "print(\"\\nLiczba brakujących wartości po czyszczeniu (tylko age):\")\n", "print(df.isnull().sum())\n", "\n", "print(f\"\\nLiczba wierszy przed czyszczeniem: {len(sns.load_dataset('titanic'))}\")\n", "print(f\"Liczba wierszy po czyszczeniu: {len(df)}\")" ], "metadata": { "id": "VvprbXwsxrSc" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Sekcja 3: Kategoryzacja opłat za bilety\n", "def categorize_fare(fare, fare_ranges):\n", " if fare <= fare_ranges[0]:\n", " return 0 # niska\n", " elif fare <= fare_ranges[1]:\n", " return 1 # średnia\n", " else:\n", " return 2 # wysoka\n", "\n", "min_fare = df['fare'].min()\n", "max_fare = df['fare'].max()\n", "fare_step = (max_fare - min_fare) / 3\n", "fare_ranges = [min_fare + fare_step, min_fare + 2 * fare_step]\n", "\n", "print(\"\\nPrzedziały cenowe biletów:\")\n", "print(f\"Niska: {min_fare:.2f} - {fare_ranges[0]:.2f}\")\n", "print(f\"Średnia: {fare_ranges[0]:.2f} - {fare_ranges[1]:.2f}\")\n", "print(f\"Wysoka: {fare_ranges[1]:.2f} - {max_fare:.2f}\")" ], "metadata": { "id": "PY0OSWJcCA9Q" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Sekcja 4: Przygotowanie danych do modelowania\n", "selected_features = ['sex', 'pclass', 'age', 'fare_category']\n", "df_model = df.copy()\n", "df_model['sex'] = df_model['sex'].map({'male': 0, 'female': 1})\n", "df_model['fare_category'] = df_model['fare'].apply(lambda x: categorize_fare(x, fare_ranges))\n" ], "metadata": { "id": "iL3tQDmmCMpq", "collapsed": true }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Sekcja 5: Podział danych i skalowanie\n", "# Przygotowanie danych\n", "X = df_model[selected_features]\n", "y = df_model['survived']\n", "\n", "# Podział na zbiór treningowy i testowy\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Skalowanie danych\n", "scaler = StandardScaler()\n", "X_train_scaled = scaler.fit_transform(X_train)\n", "X_test_scaled = scaler.transform(X_test)" ], "metadata": { "id": "3tgAa5xNEpV6", "collapsed": true }, "execution_count": null, "outputs": [] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 0 }