Learn practical skills, build real-world projects, and advance your career
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from functools import reduce
import warnings
warnings.filterwarnings('ignore')
#Setting a color palette for charts
hls=sns.color_palette("Set2")
sns.set_palette(hls)
df1 = pd.read_csv('labs.csv')
df2 = pd.read_csv('examination.csv')
df3 = pd.read_csv('demographic.csv')
df4 = pd.read_csv('diet.csv')
df5 = pd.read_csv('questionnaire.csv')
df6 = pd.read_csv('medications.csv', encoding='latin1')
data_frames = [df1, df2, df3, df4, df5,df6]
df_names = ['labs', 'examination', 'demographic', 'diet', 'questionnaire', 'medications']
for i in range(len(data_frames)):
  print('###############')
  print('Length of {} dataframe is {}'.format(df_names[i], data_frames[i].shape[0]))
  print('Unq SEQN count in {} df is {}'.format(df_names[i], str(data_frames[i].SEQN.nunique())))
print('###############')
############### Length of labs dataframe is 9813 Unq SEQN count in labs df is 9813 ############### Length of examination dataframe is 9813 Unq SEQN count in examination df is 9813 ############### Length of demographic dataframe is 10175 Unq SEQN count in demographic df is 10175 ############### Length of diet dataframe is 9813 Unq SEQN count in diet df is 9813 ############### Length of questionnaire dataframe is 10175 Unq SEQN count in questionnaire df is 10175 ############### Length of medications dataframe is 20194 Unq SEQN count in medications df is 10175 ###############