Joint Probability Matricies - Group and Merge the Data

joint_probability_matricies_3.py

# Generate a pandas dataframe where the index represents the student number
df_GT = pd.DataFrame({'bucket': bucket_GT}).reset_index()
display(df_GT.head())

df_P = pd.DataFrame({'bucket': cut_P}).reset_index()
display(df_P.head())

# Merged the actual predicted grades 
merged_df = pd.merge(df_GT, df_P, on=['index'], suffixes=('_grouth_truth', '_predicted'))
display(merged_df.head())

# Create a multi-leveled
merged_df = merged_df.groupby(['bucket_grouth_truth', 'bucket_predicted']).count()
display(merged_df.head())

# Taken from: https://stackoverflow.com/a/43921476/768439
# Convert multi-leveled pandas index into a 2d numpy array
m, n = len(merged_df.index.levels[0]), len(merged_df.index.levels[1])
jp_matrix = merged_df.values.reshape(m, n)