项目四 pandas预处理北京公交线路

import pandas as pd

# 读取 CSV 文件
bus_info = pd.read_csv('./Processed_Beijing_Bus_Info.csv')

# 去重并重置索引
bus_info1 = bus_info.drop_duplicates().reset_index(drop=True)

# 去掉缺失值并重置索引
bus_info2 = bus_info1.dropna().reset_index(drop=True)


# 清洗“总里程”列
def clean_distance(distance):
    # 如果存在 '|' 则分割
    if '|' in distance:
        distance = distance.split('|')[0]
        if '咨询' in distance:
            distance = distance.split('。')[0]
    elif '线路咨询' in distance:
        distance = distance.split('线路咨询')[0]
        if distance == '':
            distance = '没有标识'
        elif '低峰间隔' in distance or '间隔' in distance:
            distance = distance.split('。')[0]  # 处理低峰间隔
    elif ('本线路' in distance or '南沟村' in distance or '定点班车' in distance):
        distance = '没有标识'
    elif '线路' in distance:
        if '工作日' in distance:
            distance = distance.split('工作日')[0].split('。')[1]
        elif '52' in distance:
            distance = distance.split('。')[1]
        else:
            distance = distance.split('。')[0]
            if '全程' not in distance:
                distance = '没有标识'
    else:
        distance = distance.split('。')[0]
        if '全程' not in distance:
            distance = '没有标识'

    return distance


# 应用清洗函数
bus_info2['licheng'] = bus_info2['licheng'].apply(clean_distance)

# 打印清洗后的数据前五行
print("\n清洗后的数据前五行：")
print(bus_info2['licheng'].head())