Pandas Dates Exploration

import pandas as pd import numpy as np

df = pd.read_csv('sample_data.csv')

df.head()

This chart is empty

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 26 entries, 0 to 25
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   date    26 non-null     object
 1   sale    26 non-null     int64 
dtypes: int64(1), object(1)
memory usage: 544.0+ bytes

This chart is empty

df = pd.read_csv('sample_data.csv', parse_dates=['date']) df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 26 entries, 0 to 25
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype         
---  ------  --------------  -----         
 0   date    26 non-null     datetime64[ns]
 1   sale    26 non-null     int64         
dtypes: datetime64[ns](1), int64(1)
memory usage: 544.0 bytes

df.head()

# Read normally df = pd.read_csv('sample_data.csv') df.head()

df.date = pd.to_datetime(df.date, format = "%d/%m/%Y") df.head()

df = pd.read_csv('sample_data.csv', parse_dates=['date'], dayfirst=True) df.head()

df = df.set_index(['date']) df.head()

df.loc['2019-02-04':'2019-04-04']

df.loc[df.index < '03-05-2019']

df.loc['2019'].sum()

df = pd.read_csv('sample_data.csv', parse_dates= {"date" : ["year","month","day"]}, keep_date_col=True)

df['year']= df['date'].dt.year df['month']= df['date'].dt.month df['day']= df['date'].dt.day

df.head()

pd.to_datetime('today')

df.head()

df.sort_index()

pd.date_range(start='1/1/2019', end='2/01/2019')

pd.date_range(start='1/1/2019', end='2/01/2019', freq='W')

pd.to_datetime('2019-04-01') + pd.DateOffset(weeks=2)

df_temp = df.iloc[:5] df_temp

df_temp.shift(2, freq="w")

range = pd.date_range("1/1/2019", periods=28, freq="D") df = pd.Series(np.random.randint(0, 500, len(range)), index=range)

df.head()

df.resample('W').sum()

df.resample('W-MON').sum()

df.resample('W-TUE').sum()

range = pd.date_range("1/4/2019", "4/1/2019", freq="W") df = pd.Series(np.random.randint(0, 500, len(range)), index=range)

df = df.to_frame()

df.head()

df = df.drop(index=[pd.to_datetime('2019-03-03'), pd.to_datetime('2019-03-24')])

# check for missing datetimeindex values based on reference index (with all values) missing_dates = df.index[~df.index.isin(range)] missing_dates

range

df.index.get_loc(pd.to_datetime('2019-03-03'), method="nearest")

didx = df.index[df.index.get_loc(pd.to_datetime('2019-03-03'), method='nearest')] didx