import pandas as pd import numpy as np

pd.__version__

s = pd.Series()

s

data = np.array([12, 45, 32, 89]) s = pd.Series(data)

s

s = pd.Series(data, index=[101, 102, 103, 104])

s

data = {"a": 1, "b": 2, "c": 3} s = pd.Series(data)

s

data = {"a": 1, "b": 2, "c": 3} s = pd.Series(data, index=['f', 'g', 'h'])

s

data = 99 s = pd.Series(data, index=[101, 102, 103, 104])

s

data = np.array([12, 45, 32, 89, 7, -10, 21, -0.5, -7, 30]) s = pd.Series(data)

s

s[4]

s[0:3] # s[:3]

s[7:]

data = {"a": 1, "b": 2, "c": 3} s = pd.Series(data, index=['f', 'g', 'h', 'a', 'b', 'c'])

s['f':'h']

s['f'] = 88.5

s

s > 5

s[s > 2]

s.shape

s.ndim

s.size

s.index

s.values

'a' in s

s.drop('a')

s

s.drop('a', inplace=True)

s

s + 2

s - 2

s * 2

np.power(s, 2)

# empty data frame df = pd.DataFrame()

df

data = [7, 8, 44, 56, 23, 98]

df = pd.DataFrame(data)

df

data = [["dog", 'bhaw bhaw'], ['cat', 'meow'], ['cow', 'moo']] df = pd.DataFrame(data)

df

df = pd.DataFrame(data, columns=["animal_name", 'animal_sound'])

df

data = {'name': ['ram', 'rahul', 'bhwana'], "age": [25, 20, 18]} df = pd.DataFrame(data)

df

df = pd.DataFrame(data, index=['a', 'b', 'c'])

df

data = {'karan_marks': pd.Series([50, 77, 65], index=['test1', 'test2', 'test3']), "arjun_marks": pd.Series([67, 89, 32, 98, 50], index=['test-1', 'ptest-1', 'test-2', 'ptest-2', 'test-3'])} df = pd.DataFrame(data)

df

data = [{"a": 1, "b": 2}, {"c": 3, "d": 4}, {"e": 5, "f": 6}] df = pd.DataFrame(data)

df

data = [{"a": 1, "b": 2, "c": 90}, {"c": 3, "d": 4}, {"e": 5, "f": 6}] df = pd.DataFrame(data, index=['x', 'y', 'z'])

df

data = [10, 20, 30, 40, 50, 60, 70] data1 = [100, 200, 300, 400, 500, 600, 700] df = pd.DataFrame([data, data1], columns=['a', 'b', 'c', 'd', 'e', 'f', 'g'])

df

df['b']

df['h'] = [56, 78]

df

df['m'] = pd.Series([56, 78, 89])

df

df['n'] = pd.Series([56])

df

del df['n']

df

df[['c']]

df[['e', 'a', 'f']]

data = {'apple': [102, 500, 250, 75], "grapes": [50, 150, 90, 45]} df = pd.DataFrame(data)

df

df[['grapes']]

df['bananas'] = df['grapes'] + 50

df

df.drop('bananas', axis=1, inplace=True)

df

df['pear'] = df['grapes'] + 100 df['mangos'] = df['grapes'] + 500 df['jackfruit'] = df['grapes'] + 150 df['strawberry'] = df['grapes'] + 200 df['oranges'] = df['grapes'] + 70

df

# loc & iloc # loc -> works with rows df.loc[3]

# iloc -> index name df.iloc[[3]]

student_marks = { "name": ['rahul', 'rohit', 'venkat', 'sahil', 'ankita'], "OS": [25, 75.5, 96, 0, 100], "DBMS": [20, 80, 60, 50, 99] } df1 = pd.DataFrame(student_marks)

df1

data2 = {"name": "robby", "OS": 60.5, "DBMS": 55.5}

df1 = df1.append(data2, ignore_index=True)

df1

data3 = {"name": "venom", "OS": 80.5, "DBMS": 75} df3 = pd.DataFrame(data3, index=[0])

df3

df1 = pd.concat([df1, df3], ignore_index=True)

df1

df1.iloc[[0]]

df1.loc[[4]]

df1.loc[4] = ['steve', 67, 23]

df1

# del, pop, drop df1.loc[[6]]

df1.drop(6, inplace=True)

df1

lis = [1, 2, 3, 4, 5, 6, 7]

df1

df

df1

df1.head()

df1.tail()

df1.head(2)

df1.dtypes

df1.empty

df1.ndim

df1.shape

df1.size

df1.values

df1.keys()

df1.describe()

df1.T

df1.iloc[1]

df1.sum()

df1['OS'].sum()

df1['OS'].mean()

data1 = np.random.rand(10, 3) data2 = np.random.rand(7, 3)

df1 = pd.DataFrame(data1, columns=['col1', 'col2', 'col3']) df2 = pd.DataFrame(data2, columns=['col1', 'col2', 'col3'])

df1

df2

df3 = pd.concat([df1, df2], ignore_index=True)

df3

for i in df3.col3: print(i)

for key, value in df3.iterrows(): print(key, value)

unsorted_df = pd.DataFrame(np.random.randn(10, 3), index=[5, 7, 3, 9, 2, 1, 9, 11, 21, 4], columns=['col1', 'col2', 'col3'])

unsorted_df

unsorted_df.sort_index()

unsorted_df.sort_index(ascending=False)

unsorted_df.sort_index(axis=1)

df = pd.DataFrame({"apples": [50, 95, 105, 75], "grapes": [110, 45, 99, 0]})

df

df.sort_values(by='apples')

df.sort_values(by=['apples', 'grapes'])

df.sort_values(by=['apples', 'grapes'], kind='mergesort')

df3.drop([8, 16])

df3.col2

df3['col2']

df3['col2'].cov(df3['col3'])

df3['col2'].corr(df3['col3'])

df3.corr

df = pd.DataFrame(np.random.randn(5, 3), index=['a', 'c', 'e', 'b', 'd'], columns=['col1', 'col2', 'col3'])

df

df = df.reindex(['a', 'b', 'c', 'd', 'e'])

df

df.isnull()

df.notnull()

df.isnull().sum()

df.count()

df.fillna(0)