pandas学习记录

import pandas as pd

data = {'Age': [20, 30, 40, 20, 20], 'Name': ['Lucy', 'Lily', 'Andy', 'Bob', 'Tony'],
        'City': ['Bj', 'Sh', 'Gz', 'Bj', 'Bj']}
df = pd.DataFrame(data=data)

# 获取列
name_column = df['Name']

# 获取行
first_row = df.loc[0]

# 选择多列
subset = df[['Name', 'Age']]

# 过滤行
filtered_rows = df[df['Age'] > 30]

# 获取列名
columns = df.columns

# 获取形状（行数和列数）
shape = df.shape

# 获取索引
index = df.index

# 获取描述统计信息
stats = df.describe()

# 添加新列
df['Salary'] = [70000, 60000, 50000, 70000, 70000]

# 删除列
df.drop('City', axis=1, inplace=True)

# 排序
df.sort_values(by=["Age", "Salary", "Name"], ascending=[True, False, False], inplace=True)
# df = df.sort_index()

# 重命名列
df.rename(columns={'Name': 'Full Name'}, inplace=True)
print(df)

参考

• https://www.runoob.com/pandas/pandas-dataframe.html