星际争霸游戏战队案例分析

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
#1.加载并查看数据基本信息
def read_dataset(file_root):
    dataframe=pd.read_csv(file_root)
    print("数据的基本信息：")
    print(dataframe.info())
    print("数据集有%i行，%i列"%(dataframe.shape[0],dataframe.shape[1]))
    print("数据预览：")
    print(dataframe.head())
    return dataframe
#2.处理缺失数据
def processing_missing_data(dataframe):
    if (dataframe.isnull().values.any()):
        dataframe.fillna(0.)
        #dataframe.dropna()
    return dataframe
#3.可视化数据
def visualize_data(dataframe,save_fig=True):
    fig=plt.figure()
    ax1=fig.add_subplot(2,2,1)
    ax2=fig.add_subplot(2,2,2)
    ax3=fig.add_subplot(2,2,3)
    ax4=fig.add_subplot(2,2,4)
    #解决matplotlib显示中文的问题
    plt.rcParams["font.sans-serif"]=["SimHei"]#指定默认字体
    plt.rcParams["axes.unicode_minus"]=False#解决保存图像是负号显示为方块问题
    fig.suptitle("战队属性")
    ax1.scatter(dataframe["LeagueIndex"],dataframe["Age"])
    ax1.set_xlabel("战队")
    ax1.set_ylabel("年龄")
    ax2.scatter(dataframe["LeagueIndex"],dataframe["HoursPerWeek"])
    ax2.set_xlabel("战队")
    ax2.set_ylabel("每周游戏时间")
    ax3.scatter(dataframe["LeagueIndex"], dataframe["APM"])
    ax3.set_xlabel("战队")
    ax3.set_ylabel("APM")
    ax4.scatter(dataframe["LeagueIndex"], dataframe["WorkersMade"])
    ax4.set_xlabel("战队")
    ax4.set_ylabel("单位时间建造数")
    if save_fig:
        plt.savefig("H:/pythonfigure/league.png")
    plt.show()
#4.可视化数据统计
def visualize_league_data(dataframe,attribution,save_fig=True):
    min_data=[]
    max_data=[]
    mean_data=[]
    for i in range(1,9):
        filter_data=dataframe.ix[dataframe["LeagueIndex"]==i,attribution]
        min_data.append(filter_data.min())
        max_data.append(filter_data.max())
        mean_data.append(filter_data.mean())
    league_series=pd.Series(range(1,9),name="LeagueIndex")
    min_series=pd.Series(min_data,name="min")
    max_series=pd.Series(max_data,name="max")
    mean_series=pd.Series(mean_data,name="mean")
    dataframe_rst=pd.concat([league_series,min_series,max_series,mean_series],axis=1)
    if save_fig:
        dataframe_rst.to_csv("H:/pythonfigure/min_max_mean.csv")
    #统计值可视化
    fig=plt.figure()
    ax1=fig.add_subplot(1,1,1)
    #解决matplotlib显示中文问题
    plt.rcParams["font.sans-serif"]=["SimHei"]#指定默认字体
    plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
    ax1.plot(dataframe_rst["LeagueIndex"],dataframe_rst["min"],color='b')
    ax1.plot(dataframe_rst["LeagueIndex"],dataframe_rst["max"],color='g')
    ax1.plot(dataframe_rst["LeagueIndex"],dataframe_rst["mean"],color="r")
    ax1.set_xlabel("战队")
    ax1.set_ylabel("attribution")
    ax1.legend()
    if save_fig:
        plt.savefig("H:/pythonfigure/min_max_mean.png")
    plt.show()

#加载数据
dataframe=read_dataset("H:/pythonfigure/starcraft.csv")
#处理缺失数据
df_data=processing_missing_data(dataframe)
#可视化数据
visualize_data(df_data,save_fig=True)
#可视化统计指标
visualize_league_data(df_data,"Age",save_fig=True)
visualize_league_data(df_data,"HoursPerWeek",save_fig=True)
visualize_league_data(df_data,"APM",save_fig=True)
visualize_league_data(df_data,"WorkersMade",save_fig=True)