Pandas Tutorials [Notions : 1/12]

Pandas Tutorials

Pandas is a Python library for data manipulation and analysis, and can be conveniently used to process large amounts of data. An introduction to the basic use of Pandas. Examples and explanations refer to pandas official documentation.
Ref link : https://codetorial.net/pandas/index.html

# Importing module
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

Pandas Object Tutorials

• Series : 레이블을 가지는 1차원 어레이
• DataFrame : 레이블 갖는 행x열 구조의 2차원 어레이

s = pd.Series([1,2,3,4,5,6])
t = pd.Series([1,2,3,4,5,6.3])
print(s)
print(t)

s = pd.Series([1,2,3,4.5,5,6], index=['a', 'b', 'c', 'd', 'e', 'f'])
s

dates = pd.date_range('20230112', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(dates)
print(df)

df2 = pd.DataFrame({'A': 1.,
                  '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(df2)
print(df2.dtypes)

df3 = pd.read_csv('./assets/pandas_ex01.csv', header=None)
df3

df4 = pd.read_csv('./assets/pandas_ex02.csv', header=0)
df4

df5 = pd.read_csv('./assets/pandas_ex02.csv', index_col=0)
df5

Pandas Viewing Data

• df.head()
• df.tail()
• df.index()
• df.columns()
• df.to_numpy()
• df.describe()
• df.T()
• df.sort_index()
• df.sort_values()

dates = pd.date_range('20230405', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df

df.head(2)

df.tail(4)

df.index

df.columns

df.to_numpy()

df.describe()

print(df)
print()
print(df.T)

df.sort_index(axis=1, ascending=False)
df.sort_values(by='B')

Pandas Data Selection

• df.loc()
• df.iloc()
• df.at()
• df.iat()
• df.isin()

np.random.seed(0)

dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))

print(dates)
print(df)

# 열 선택하기
print(df['A'])
#print(df.A)
print(type(df['A']))

# 행 선택하기
print(df[0:3])

# 레이블로 선택하기
print(df.loc[dates[0]])

print(df.loc[:, ['A', 'B']])

print(df.loc['20130104', ['A', 'B']])
# A    0.761038
# B    0.121675
# Name: 2013-01-04 00:00:00, dtype: float64

df.loc[dates[0], 'A']
# 1.764052345967664

df.at[dates[0], 'A']
# 1.764052345967664

print(df)
print()
print(df.iloc[3]) # df.iloc[row position, col position]

print(df)
print()
print(df.iloc[2:4, 0:3])

print(df)
print()
print(df.iloc[[1,2,4], [0, 3]])

print(df)
print()
print(df.iloc[5, 3])

print(df)
print()
print(df.iat[5, 3])

print(df)
print()
print(df.A > 2)

print(df)
print()
print(df[df>1])

df2 = df.copy()
df2['E'] = ['one', 'one', 'two', 'three', 'four', 'three']

print(df2)
print()
print(df2[df2['E'].isin(['two', 'four'])]) # Filtering

s1 = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range('20130102', periods=6))
print(s1)

print()

df['F'] = s1
print(df)

df.at[dates[0], 'A'] = 0

print(df)

df.iat[0, 1] = 0

print(df)

df.loc[:, 'D'] = np.array([5] * len(df))

print(df)

df2 = df.copy()
df2[df2 > 0] = -df2

print(df2)