Python 2.x에서 데이터 분석을 위해 pandas 모듈을 사용하는 방법

pip install pandas

import pandas as pd

# 创建一个Series对象
data = pd.Series([1, 3, 5, np.nan, 6, 8])

print(data)

0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

import pandas as pd
import numpy as np

# 创建一个DataFrame对象
data = pd.DataFrame({
    "A": [1, 2, 3, 4],
    "B": pd.Timestamp('20130102'),
    "C": pd.Series(1, index=list(range(4)), dtype='float32'),
    "D": np.array([3] * 4, dtype='int32'),
    "E": pd.Categorical(["test", "train", "test", "train"]),
    "F": 'foo'
})

print(data)

   A          B    C  D      E    F
0  1 2013-01-02  1.0  3   test  foo
1  2 2013-01-02  1.0  3  train  foo
2  3 2013-01-02  1.0  3   test  foo
3  4 2013-01-02  1.0  3  train  foo

import pandas as pd

# 从CSV文件中读取数据
data = pd.read_csv('data.csv')

print(data.head())

import pandas as pd

# 从Excel文件中读取数据
data = pd.read_excel('data.xlsx')

print(data.head())

import pandas as pd

# 读取数据
data = pd.read_csv('data.csv')

# 统计描述性统计信息
print(data.describe())

# 计算各列之间的相关系数
print(data.corr())

import pandas as pd

# 读取数据
data = pd.read_csv('data.csv')

# 筛选出满足条件的数据
filtered_data = data[data['age'] > 30]

# 按照某列进行排序
sorted_data = data.sort_values('age')

print(filtered_data.head())
print(sorted_data.head())

import pandas as pd

# 读取数据
data = pd.read_csv('data.csv')

# 按照某一列进行分组
grouped_data = data.groupby('gender')

# 计算每组的平均值
mean_data = grouped_data.mean()

print(mean_data)

import pandas as pd

# 读取数据
data = pd.read_csv('data.csv')

# 将数据写入到CSV文件中
data.to_csv('output.csv', index=False)

# 将数据写入到Excel文件中
data.to_excel('output.xlsx', index=False)