Digitize scikit-learn's classification_report

classification_report_parse.py

from io import StringIO
import pandas as pd
import numpy as np
import sklearn
def parse_classification_report(classification_report):
    """Parses sklearn classification report into a pandas dataframe."""
    return pd.read_fwf(StringIO(classification_report),lineterminator='\n', index_col=0, colspecs=[(0,12),(12,22),(22,32),(32,42),(42,52)]).dropna()

  target_names['leak','no leak']

y_pred = np.random.random(100)>0.5
y_true = np.random.random(100)>0.5
s = sklearn.metrics.classification_report(y_true,y_pred,target_names=target_names)
parse_classification_report(s).to_dict()

"""
{'f1-score': {'avg / total': 0.41999999999999998,
  'leak': 0.40000000000000002,
  'no leak': 0.44},
 'precision': {'avg / total': 0.42999999999999999,
  'leak': 0.35999999999999999,
  'no leak': 0.48999999999999999},
 'recall': {'avg / total': 0.41999999999999998,
  'leak': 0.44,
  'no leak': 0.40000000000000002},
 'support': {'avg / total': 100.0, 'leak': 43.0, 'no leak': 57.0}}
 """