Created
September 29, 2020 19:36
-
-
Save SaraM92/b9479a28e1d9d233432ec108e2f35c12 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Import Pnadas to deal with datasets | |
import pandas as pd | |
#Dataset source | |
#https://www.kaggle.com/dipam7/student-grade-prediction | |
df = pd.read_csv('student-mat.csv') | |
df.head(3) | |
#student achieved 80% or higher as a final score | |
df['grade_A'] = np.where(df['G3']*5 >= 80, 1, 0) | |
#value of 1 if a student missed 10 or more classes | |
df['high_absenses'] = np.where(df['absences'] >= 10, 1, 0) | |
#drop all columns we don’t care about | |
df = df[['grade_A','high_absenses','count']] | |
df.head() | |
pd.pivot_table( | |
df, | |
values='count', | |
index=['grade_A'], | |
columns=['high_absenses'], | |
aggfunc=np.size, | |
fill_value=0 | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment