Pradeep Singh mepsrajput

🎯

Focusing

ML Engineer

mepsrajput / sas-proc-means.sas

Created April 24, 2022 08:14

	title "Simple proc means";

	/* Simple proc means */
	PROC MEANS DATA=SASHELP.CARS;
	RUN;

	title "Select the required variables & drop the labels";
	/* Select the variables & drop the labels */
	PROC MEANS DATA=SASHELP.CARS nolabels;
	var

mepsrajput / multiple-freq.py

Last active April 23, 2022 17:52

	from IPython.display import display

	def multiFreq(dataset, variable_list):
	for i in variable_list:
	datax = dataset[f'{i}'].value_counts()
	datay = pd.DataFrame({
	f'{i}': datax.index,
	'Frequency': datax.values,
	'Percent': ((datax.values/datax.values.sum())*100).round(2),
	'Cumulative Frequency': datax.values.cumsum(),

mepsrajput / proc-freq-multiple.sas

Created April 23, 2022 17:47

	/* freq procedure with multiple variables */
	proc freq data=hgrosser;
	tables GENRE MOVIE;
	run;

mepsrajput / proc_freq_with_missing.py

Created April 14, 2022 16:40

	datax = data['GENRE'].value_counts(dropna=False)
	datay = pd.DataFrame({
	'GENRE': datax.index,
	'Frequency': datax.values,
	'Percent': ((datax.values/datax.values.sum())*100).round(2),
	'Cumulative Frequency': datax.values.cumsum(),
	'Cumulative Percent': ((datax.values.cumsum()/datax.values.sum())*100).round(2)
	})

	datay

mepsrajput / freq_procedure_with_missing.sas

Last active April 14, 2022 16:35

mepsrajput / freq_crosstab.py

Created April 14, 2022 14:51

	datab = pd.crosstab(data.county, data.state, margins=True, margins_name='Total')

	datab

mepsrajput / freq_cross_tab.sas

Created April 14, 2022 14:50

	proc freq data=Gov_C_SAS;
	tables county*state / norow nocol nopercent;
	run;

mepsrajput / proc_freq_options.py

Last active April 14, 2022 14:48

	datax = data['state'].value_counts().sort_index()
	datay = pd.DataFrame({
	'state': datax.index,
	'Frequency': datax.values
	})

	datay

mepsrajput / proc_freq_options.sas

Created April 14, 2022 14:45

	proc freq data = Gov_C_SAS;
	tables state / nopercent nocum;
	run;

mepsrajput / proc_freq_descending.py

Created April 14, 2022 14:42

	datax = data['state'].value_counts()
	datay = pd.DataFrame({
	'state': datax.index,
	'Frequency': datax.values,
	'Percent': ((datax.values/datax.values.sum())*100).round(2),
	'Cumulative Frequenc': datax.values.cumsum(),
	'Cumulative Percen':((datax.values.cumsum()/datax.values.sum())*100).round(2)
	})

	datay