scikit learn output metrics.classification_report into CSV/tab-delimited format

Question

I\'m doing a multiclass text classification in Scikit-Learn. The dataset is being trained using the Multinomial Naive Bayes classifier having hundreds of labels. Here\'s an extr

Answer 1

def to_table(report):
    report = report.splitlines()
    res = []
    res.append(['']+report[0].split())
    for row in report[2:-2]:
       res.append(row.split())
    lr = report[-1].split()
    res.append([' '.join(lr[:3])]+lr[3:])
    return np.array(res)

returns a numpy array which can be turned to pandas dataframe or just be saved as csv file.

Answer 2

I don't know if you still need a solution or not but this is best I have done to keep it in perfect format and still save it:

def classifcation_report_processing(model_to_report):
    tmp = list()
    for row in model_to_report.split("\n"):
        parsed_row = [x for x in row.split("  ") if len(x) > 0]
        if len(parsed_row) > 0:
            tmp.append(parsed_row)

    # Store in dictionary
    measures = tmp[0]

    D_class_data = defaultdict(dict)
    for row in tmp[1:]:
        class_label = row[0]
        for j, m in enumerate(measures):
            D_class_data[class_label][m.strip()] = float(row[j + 1].strip())
    save_report = pd.DataFrame.from_dict(D_class_data).T
    path_to_save = os.getcwd() +'/Classification_report.xlsx'
    save_report.to_excel(path_to_save, index=True)
    return save_report.head(5)


saving_CL_report_naive_bayes = classifcation_report_processing(classification_report(y_val, prediction))

Answer 3

If you want the individual scores this should do the job just fine.

import pandas as pd

def classification_report_csv(report):
    report_data = []
    lines = report.split('\n')
    for line in lines[2:-3]:
        row = {}
        row_data = line.split('      ')
        row['class'] = row_data[0]
        row['precision'] = float(row_data[1])
        row['recall'] = float(row_data[2])
        row['f1_score'] = float(row_data[3])
        row['support'] = float(row_data[4])
        report_data.append(row)
    dataframe = pd.DataFrame.from_dict(report_data)
    dataframe.to_csv('classification_report.csv', index = False)

report = classification_report(y_true, y_pred)
classification_report_csv(report)

Answer 4

The simplest and best way I found is:

classes = ['class 1','class 2','class 3']

report = classification_report(Y[test], Y_pred, target_names=classes)

report_path = "report.txt"

text_file = open(report_path, "w")
n = text_file.write(report)
text_file.close()

Answer 5

I also found some of the answers a bit verbose. Here is my three line solution, using precision_recall_fscore_support as others have suggested.

import pandas as pd
from sklearn.metrics import precision_recall_fscore_support

report = pd.DataFrame(list(precision_recall_fscore_support(y_true, y_pred)),
            index=['Precision', 'Recall', 'F1-score', 'Support']).T

# Now add the 'Avg/Total' row
report.loc['Avg/Total', :] = precision_recall_fscore_support(y_true, y_test,
    average='weighted')
report.loc['Avg/Total', 'Support'] = report['Support'].sum()

Answer 6

We can get the actual values from the precision_recall_fscore_support function and then put them into data frames. the below code will give the same result, but now in pandas df :).

clf_rep = metrics.precision_recall_fscore_support(true, pred)
out_dict = {
             "precision" :clf_rep[0].round(2)
            ,"recall" : clf_rep[1].round(2)
            ,"f1-score" : clf_rep[2].round(2)
            ,"support" : clf_rep[3]
            }
out_df = pd.DataFrame(out_dict, index = nb.classes_)
avg_tot = (out_df.apply(lambda x: round(x.mean(), 2) if x.name!="support" else  round(x.sum(), 2)).to_frame().T)
avg_tot.index = ["avg/total"]
out_df = out_df.append(avg_tot)
print out_df