Pandas Session 4 Code

Pandas Session 4 Code For Video Click Fahad Hussain CS

Hi, Welcome to Fahad Hussain CS blog, do not forget to subscribe and follow the blog and YouTube channel  Fahad Hussain CS

Code:

### Arithmetic and Data Alignment

s1 = pd.Series([7.3, -2.5, 3.4, 1.5], index=['a', 'c', 'd', 'e'])

s2 = pd.Series([-2.1, 3.6, -1.5, 4, 3.1],

               index=['a', 'c', 'e', 'f', 'g'])

print(s1)

print(s2)

print(s1 + s2)

df1 = pd.DataFrame(np.arange(9.).reshape((3, 3)), columns=list('bcd'),

                   index=['Ohio', 'Texas', 'Colorado'])

df2 = pd.DataFrame(np.arange(12.).reshape((4, 3)), columns=list('bde'),

                   index=['Utah', 'Ohio', 'Texas', 'Oregon'])

print(df1)

print(df2)

print(df1 - df2)

df1 = pd.DataFrame({'A': [1, 2]})

df2 = pd.DataFrame({'B': [3, 4]})

print(df1)

print(df2)

print(df1 - df2)

## Arithmetic methods with fill values

import numpy as np

df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)),

                   columns=list('abcd'))

df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)),

                   columns=list('abcde'))

print(df1)

print(df2)

df2.loc[1, 'b'] = np.nan

print(df1)

print(df2)

df1 + df2

df1.add(df2, fill_value=0)

print(1 / df1)

print(df1.div(1))

df1.reindex(columns=df2.columns, fill_value=0)

## Operations between DataFrame and Series

arr = np.arange(12.).reshape((3, 4))

print(arr)

print(arr[0])

print(arr - arr[0])

frame = pd.DataFrame(np.arange(12.).reshape((4, 3)),

                     columns=list('bde'),

                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])

series = frame.iloc[0]

print(frame)

print(series)

frame - series

series = pd.Series(range(3), index=['b', 'e', 'f'])

print(frame + series2)

series3 = frame['d']

print(frame)

print(series3)

print(frame.sub(series3, axis='index'))

## Function Application and Mapping

frame = pd.DataFrame(np.random.randn(4, 3), columns=list('bde'),

                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])

print(frame)

print(np.abs(frame))

f = lambda x: x.max() - x.min()

frame.apply(f)

frame.apply(f, axis='columns')

def f(x):

    return pd.Series([x.min(), x.max()], index=['min', 'max'])

frame.apply(f)

format = lambda x: '%.2f' % x

frame.applymap(format)

frame['e'].map(format)

## Sorting and Ranking

obj = pd.Series(range(4), index=['d', 'a', 'b', 'c'])

obj.sort_index()

frame = pd.DataFrame(np.arange(8).reshape((2, 4)),

                     index=['three', 'one'],

                     columns=['d', 'a', 'b', 'c'])

print(frame.sort_index())

print(frame.sort_index(axis=1))

frame.sort_index(axis=1, ascending=False)

obj = pd.Series([4, 7, -3, 2])

obj.sort_values()

obj = pd.Series([4, np.nan, 7, np.nan, -3, 2])

obj.sort_values()

frame = pd.DataFrame({'b': [4, 7, -3, 2], 'a': [0, 1, 0, 1]})

print(frame)

print(frame.sort_values(by='b'))

frame.sort_values(by=['a', 'b'])

obj = pd.Series([7, -5, 7, 4, 2, 0, 4])

obj.rank()

obj.rank(method='first')

# Assign tie values the maximum rank in the group

obj.rank(ascending=False, method='max')

frame = pd.DataFrame({'b': [4.3, 7, -3, 2], 'a': [0, 1, 0, 1],

                      'c': [-2, 5, 8, -2.5]})

frame

frame.rank(axis='columns')

##Axis Indexes with Duplicate Labels

obj = pd.Series(range(5), index=['a', 'a', 'b', 'b', 'c'])

obj

obj.index.is_unique

print(obj['a'])

print(obj['c'])

df = pd.DataFrame(np.random.randn(4, 3), index=['a', 'a', 'b', 'b'])

df

df.loc['b']