justinhchae’s gists

justinhchae / grouper_example5.py

Last active January 12, 2021 15:27

	import plotly.graph_objects as go
	import plotly_express as px

	# group the dataframe
	group = df.groupby('types')

	# create a blank canvas
	fig = go.Figure()

	# each group iteration returns a tuple

justinhchae / grouper_example4.py

Last active January 12, 2021 14:59

	import plotly.graph_objects as go
	import plotly_express as px

	# group the dataframe
	group = df.groupby('types')

	# create a blank canvas
	fig = go.Figure()

	# each group iteration returns a tuple

justinhchae / grouper_example3.py

Last active January 12, 2021 15:11

	gitcsv = 'https://raw.githubusercontent.com/justinhchae/medium/main/sample.csv'
	df = pd.read_csv(gitcsv, index_col=0)

	df['dates'] = pd.to_datetime(df['dates'])

	freq='M'

	df = df.groupby(['types', pd.Grouper(key='dates', freq=freq)])['types'].agg(['count']).reset_index()

justinhchae / grouper_example2.py

Last active January 12, 2021 02:59

	freq='M'
	# or 'D' or 'Y'
	df = df[['dates', 'types']].groupby([pd.Grouper(key='dates', freq=freq)]).agg('count').reset_index()

	"""
	dates count
	2 2012-07-31 0
	1 2012-06-30 1
	3 2012-08-31 1
	0 2012-05-31 2

justinhchae / grouper_example1.py

Last active January 12, 2021 15:45

justinhchae / simple_lambdas_example.py

Last active January 1, 2021 02:15

Another example of a lambdas that changes all values

	# replace all values with the same thing
	df[col1] = df[col1].apply(lambda x: x.replace(year=2109, month=1, day=1))
	print(df[col1].head(2))

	# output

	"""
	event_date
	2109-01-01
	2109-01-01

justinhchae / simple_lambdas_ondf.py

Created December 30, 2020 22:14

A simple, do nothing lambdas function on a DataFrame

	# copy col2 value into a new column
	col_new = str(col1 + '_new')
	df[col_new] = df.apply(lambda x: x[col2] , axis=1)
	print(df[[col1, col_new, col2]].head(2))

	# output

	"""
	event_date event_date_new received_date
	2011-01-05 2011-01-31 2011-01-31

justinhchae / lambda_pandas_one_conditiona.py

Last active January 1, 2021 02:15

Lambdas on Pandas DF with apply and one conditional

	# replace col1 year with col2 year on a condition
	# if does not meet condition, use the original col1 value
	df[col_new] = df.apply(lambda x: x[col1].replace(year=x[col2].year)
	if x[col1].year > curr_year else x[col1]
	, axis=1)

	# filter df where year is greater than current year
	df = df[(df[col1].dt.year > curr_year)]
	print(df[[col1, col_new, col2]].head(2))
	# output

justinhchae / lambda_pandas_two_conditionals.py

Last active January 3, 2021 20:24

Lambda function with two conditional statements

	# lambda with two conditional statements
	df[col_new] = df.apply(lambda x: x[col1].replace(year=x[col2].year) if x[col1].year > curr_year
	else x[col1].replace(year=x[col2].year) if x[col1].year < past_year
	else x[col1]
	, axis=1)

justinhchae / impute_lambdas_changelog.py

Last active January 1, 2021 02:17

impute dates with apply and lambdas with change log

	# store the lambda function as an object
	impute = lambda x: x[col1].replace(year=x[col2].year) if x[col1].year > curr_year \
	else x[col1].replace(year=x[col2].year) if x[col1].year < past_year \
	else x[col1]

	# simplify the code later by calling impute
	df[col_new] = df.apply(impute, axis=1)

	# a new dataframe called change_log
	change_log = df[(df[col1].dt.year > curr_year)]