demo.py:
# coding=utf-8
import numpy as np
import pandas as pd
df1 = pd.DataFrame(np.arange(12, 24).reshape((3,4)), columns=["W","X","Y","Z"])
print(df1)
'''
W X Y Z
0 12 13 14 15
1 16 17 18 19
2 20 21 22 23
'''
print(df1.index) # RangeIndex(start=0, stop=3, step=1)
print(df1.columns) # Index(['W', 'X', 'Y', 'Z'], dtype='object')
print(type(df1.values)) # <class 'numpy.ndarray'>
print(df1.values)
'''
[[12 13 14 15]
[16 17 18 19]
[20 21 22 23]]
'''
print(df1.shape) # (3, 4)
print(df1.ndim) # 2 维度
print(df1.dtypes) # 每一列的数据类型
'''
W int64
X int64
Y int64
Z int64
dtype: object
'''
print(df1.head(2)) # 显示前几行。默认前5行
'''
W X Y Z
0 12 13 14 15
1 16 17 18 19
'''
print(df1.tail(2)) # 显示末尾几行。默认末尾5行
'''
W X Y Z
1 16 17 18 19
2 20 21 22 23
'''
# 展示DataFrame的概览
print(df1.info())
'''
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 4 columns):
W 3 non-null int64
X 3 non-null int64
Y 3 non-null int64
Z 3 non-null int64
dtypes: int64(4)
memory usage: 176.0 bytes
None
'''
# 显示DataFrame的统计信息 (只能统计数值类型的列)
print(df1.describe()) # mean均值 std标准差 50%中位数 25%四分位数
'''
W X Y Z
count 3.0 3.0 3.0 3.0
mean 16.0 17.0 18.0 19.0
std 4.0 4.0 4.0 4.0
min 12.0 13.0 14.0 15.0
25% 14.0 15.0 16.0 17.0
50% 16.0 17.0 18.0 19.0
75% 18.0 19.0 20.0 21.0
max 20.0 21.0 22.0 23.0
'''