mepsrajput

/* Import the CSV */

FILENAME Gov_C "/folders/myfolders/Assignments/governors_county.csv";

PROC IMPORT DATAFILE=Gov_C DBMS=CSV OUT=WORK.Gov_C_SAS;
	GETNAMES=YES;
RUN;

/* freq procedure */
proc freq data=Gov_C_SAS;

mepsrajput

# Import Pandas
import pandas as pd

# Import CSV
data = pd.read_csv("../input/us-election-2020/governors_county.csv");

# Frequencies in Actual Order
datax = data['state'].value_counts().sort_index()

# Create a dataframe

mepsrajput

/* Proc freq with descending order */
proc freq data=Gov_C_SAS order=freq;
    tables state;
run;

mepsrajput

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

mepsrajput

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

mepsrajput

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

datay

mepsrajput

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

mepsrajput

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

datab

mepsrajput

/* freq procedure with missing */
proc freq data=Gov_C_SAS;
	tables GENRE / missing;
run;

mepsrajput

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