Python数据处理的三个实用技巧分享

>>> import pandas as pd
>>> pd.__version__
'0.25.1'

>>> import os
>>> os.chdir('D://source/dataset') # 这是我的数据集所在目录
>>> os.listdir() # 确认此目录已经存在 IMDB-Movie-Data 数据集
['drinksbycountry.csv', 'IMDB-Movie-Data.csv', 'movietweetings', 'titanic_eda_data.csv', 'titanic_train_data.csv']

>>> df = pd.read_csv("IMDB-Movie-Data.csv")
>>> df.head(1) # 导入并显示第一行
   Rank                    Title                    Genre  ...   Votes Revenue (Millions) Metascore
0     1  Guardians of the Galaxy  Action,Adventure,Sci-Fi  ...  757074             333.13      76.0

[1 rows x 12 columns]

>>> meta = df.pop("Title").to_frame() # 移除 Title 列

>>> df.head(1) # df 变为 11列
   Rank                    Genre  ... Revenue (Millions) Metascore
0     1  Action,Adventure,Sci-Fi  ...             333.13      76.0

[1 rows x 11 columns]

>>> meta.head(3)
                     Title
0  Guardians of the Galaxy
1               prometheus
2                    Split

# .str.count(" ") + 1 得到单词个数 
>>> meta["Words_count"] = meta["Title"].str.count(" ") + 1 
>>> meta.head(3) # words_count 列代表单词个数
                     Title  words_count
0  Guardians of the Galaxy            4
1               Prometheus            1
2                    Split            1

>>> vc = df["Genre"].value_counts()

>>> vc.head()
Action,Adventure,Sci-Fi    50
Drama                      48
Comedy,Drama,Romance       35
Comedy                     32
Drama,Romance              31
Name: Genre, dtype: int64

>>> import matplotlib.pyplot as plt
>>> vc[:5].plot(kind='pie')
<matplotlib.axes._subplots.AxesSubplot object at 0x000001D65B114948>
>>> plt.show()