df.drop(index = 4)

deleting with index

country_grp['Salary'].median().loc['Germany'] Germany country looking for the Salary

country_uses_python = country_grp['LanguageWorkedWith'].apply(lambda x: x.str.contains('Python').sum())

where Python word contains

df.columns = df.columns.str.replace('', '_')

df.columns = [x.upper() for x in df.columns]

df.apply(len, axis='columns')


df['email'].apply(len)

len(df['email'])

df['full_name'] = df['first'] + '' + df['last']

adding columsn

df.drop(columns = ['first', ' last'], inplace = True)

removing column

df[['first', 'last']] = df['full_name'].str.split(' ', expand = True)

mergin two columns as one

df.dropna(axis ='index', how ='all', subset=['last', 'email'])


droping null values with specfiying indexes

df['age'] = df['age'].astype(float)


working with missing values

df['YearsCode'].unique()

getting only unique values

df['date'] = pd.to_datetime(df.date, dayfirst=True)
# df['month'] = df['date'].dt.month
# df['month_year'] = df['full_datetime'].dt.strftime('%m-%Y')
# df['date'] = df['date'].dt.to_period('M')



when working with dates

Numpy

x = np.array([-1,0,1.4],dtype='bool')
y = np.array([-1,0,1.4],dtype='int16')
z = np.array([-1,0,1.4],dtype='float64')

it says boolean works faster