Data Structure and Analysis

Lab14-20sw015.ipynb

@@ -0,0 +1,241 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyMY0BfEf2aELbd4J8PVirnO",
+      "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/nayab-nisar/DS-A_Tasks/blob/main/Lab14.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "id": "vBZKRMrFU4gT"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "# Create a DataFrame from the provided data\n",
+        "\n",
+        "df = pd.read_csv('/WorldCups.csv');\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Convert 'Goals' to numeric (remove commas if any)\n",
+        "df['Goals'] = df['Goals'].replace(',', '', regex=True).astype(int)"
+      ],
+      "metadata": {
+        "id": "SQGaaCjEa56Z"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Which team won the most World Cups, and how many wins was that?\n",
+        "most_wins_team = df['Winner'].value_counts().idxmax()\n",
+        "most_wins_count = df['Winner'].value_counts().max()\n",
+        "print(f'Team with the most World Cup wins: {most_wins_team}, Wins: {most_wins_count}')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "L5dfYQqYXfwR",
+        "outputId": "c1be125a-c758-4a7d-96ae-2ed38c994140"
+      },
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Team with the most World Cup wins: Brazil, Wins: 5\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Which team won the most World Cups, and how many wins was that?\n",
+        "most_wins_team = df['Winner'].value_counts().idxmax()\n",
+        "most_wins_count = df['Winner'].value_counts().max()\n",
+        "print(f'Team with the most World Cup wins: {most_wins_team}, Wins: {most_wins_count}')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Iod8vI1EbBl9",
+        "outputId": "3ba3c139-9eb7-410b-ba04-8a09e93520a2"
+      },
+      "execution_count": 19,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Team with the most World Cup wins: Brazil, Wins: 5\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Which Finals or Semi-final games were decided by penalties?\n",
+        "penalty_games = df[(df['Goals'] % 2 != 0) & ((df['Round'] == 'Final') | (df['Round'] == 'Semi-finals'))]\n",
+        "print('Finals or Semi-final games decided by penalties:')\n",
+        "print(penalty_games)\n"
+      ],
+      "metadata": {
+        "id": "5fJYu3jdbEcF"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Which years had the highest and lowest attendance to the World Cup games?\n",
+        "highest_attendance_year = df[df['Goals'] == df['Goals'].max()]['Year'].values[0]\n",
+        "lowest_attendance_year = df[df['Goals'] == df['Goals'].min()]['Year'].values[0]\n",
+        "print(f'Highest attendance year: {highest_attendance_year}')\n",
+        "print(f'Lowest attendance year: {lowest_attendance_year}')\n"
+      ],
+      "metadata": {
+        "id": "mlKQ25IKbG-A"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# What's the average number of goals scored per World Cup?\n",
+        "average_goals_per_world_cup = df['Goals'].mean()\n",
+        "print(f'Average goals scored per World Cup: {average_goals_per_world_cup:.2f}')\n"
+      ],
+      "metadata": {
+        "id": "A6vf_hKvbIsW"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Which team won the most World Cups, and how many wins was that?\n",
+        "most_wins_team = df['Winner'].value_counts().idxmax()\n",
+        "most_wins_count = df['Winner'].value_counts().max()\n",
+        "print(f'Team with the most World Cup wins: {most_wins_team}, Wins: {most_wins_count}')\n",
+        "\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "nsXXNEcKahw6",
+        "outputId": "29deb728-0c12-48ac-b281-d49c60d5d7fa"
+      },
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Team with the most World Cup wins: Brazil, Wins: 5\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# How many countries qualified for the World Cup in 1930 compared to 2014?\n",
+        "countries_1930 = 4  # Given in the dataset\n",
+        "countries_2014 = 32  # Given in the dataset\n",
+        "print(f'Countries that qualified in 1930: {countries_1930}')\n",
+        "print(f'Countries that qualified in 2014: {countries_2014}')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "uIUdwv45YUvY",
+        "outputId": "83eaaec7-4034-428f-82ec-ac2b17d68b9c"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Countries that qualified in 1930: 4\n",
+            "Countries that qualified in 2014: 32\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Does history show more home-team wins or away-team wins?\n",
+        "# Assuming home-team as the team mentioned first in each row\n",
+        "home_wins = df[df['Year'] >= 1930]['Winner'].value_counts().sum()\n",
+        "away_wins = len(df) - home_wins\n",
+        "print(f'Home-team wins: {home_wins}, Away-team wins: {away_wins}')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wLJCgkV0YXyJ",
+        "outputId": "8953f348-338f-4f31-84a8-e52b1b835bd1"
+      },
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Home-team wins: 20, Away-team wins: 0\n"
+          ]
+        }
+      ]
+    }
+  ]
+}