27 lines
551 B
Python
27 lines
551 B
Python
|
# %%
|
||
|
|
import pandas as pd
|
||
|
|
|
||
|
|
# %%
|
||
|
|
data_path = '../../data_preprocess/exports/preprocessed_data.csv'
|
||
|
|
full_df = pd.read_csv(data_path, skipinitialspace=True)
|
||
|
|
|
||
|
|
# %%
|
||
|
|
df_in = full_df[full_df['MDM']].reset_index(drop=True)
|
||
|
|
# %%
|
||
|
|
df_out = full_df[~full_df['MDM']].reset_index(drop=True)
|
||
|
|
# %%
|
||
|
|
label_counts_in = df_in['unit'].value_counts()
|
||
|
|
print(label_counts_in.to_string())
|
||
|
|
|
||
|
|
# %%
|
||
|
|
label_counts_out = df_out['unit'].value_counts()
|
||
|
|
print(label_counts_out.to_string())
|
||
|
|
|
||
|
|
|
||
|
|
# %%
|
||
|
|
label_counts_out['NOVALUE']/len(df_out)
|
||
|
|
|
||
|
|
# %%
|
||
|
|
label_counts_in['NOVALUE']/len(df_out)
|
||
|
|
# %%
|