def display_logistic_regression(df, train_x, valid_x, train_y, valid_y):
print('(8) Display logistic regression\n')
# fit a logistic regression (set penalty=l2 and C=1e42 to avoid regularization)
logit_reg = LogisticRegression(penalty='l2', C=1e42, solver='liblinear')
logit_reg.fit(train_x, train_y)
print('intercept ', logit_reg.intercept_[0])
print(
pd.DataFrame({'coeff': sorted(abs(logit_reg.coef_[0]), reverse=True)},
index=PREDICTORS), '\n')
print(
'AIC',
AIC_score(valid_y,
logit_reg.predict(valid_x),
df=len(train_x.columns) + 1))
classificationSummary(train_y, logit_reg.predict(train_x))
classificationSummary(valid_y, logit_reg.predict(valid_x))
prediction_valid = logit_reg.predict(valid_x)
prediction_train = logit_reg.predict(train_x)
print('precision on test is:', precision_score(valid_y, prediction_valid))
print('recall on test is:', recall_score(valid_y, prediction_valid))
print('f1 on test is:', f1_score(valid_y, prediction_valid))
print('Logistic Regression:Accuracy on train is:',
accuracy_score(train_y, prediction_train))
print('Logistic Regression:Accuracy on test is:',
accuracy_score(valid_y, prediction_valid), '\n')
def test_classificationSummary(self):
y_true = [1, 0, 0, 1, 1, 1]
y_pred = [1, 0, 1, 1, 0, 0]
out = StringIO()
with redirect_stdout(out):
classificationSummary(y_true, y_pred, class_names=['a', 'b'])
s = out.getvalue()
self.assertIn('Confusion Matrix', s)
self.assertIn(' Prediction', s)
self.assertIn('a 1 1', s)
self.assertIn('b 2 2', s)
def test_classificationSummary(self):
y_true = [1, 0, 0, 1, 1, 1]
y_pred = [1, 0, 1, 1, 0, 0]
out = StringIO()
with redirect_stdout(out):
classificationSummary(y_true, y_pred, class_names=['a', 'b'])
s = out.getvalue()
self.assertIn('Confusion Matrix', s)
self.assertIn(' Prediction', s)
self.assertIn('a 1 1', s)
self.assertIn('b 2 2', s)
lines = s.split('\n')
self.assertEqual(lines[0], 'Confusion Matrix (Accuracy 0.5000)')
self.assertEqual(lines[3], 'Actual a b')
self.assertEqual(lines[4], ' a 1 1')
true_y = y == 'default'
true_pos = true_y & pred_y
true_neg = ~true_y & ~pred_y
false_pos = ~true_y & pred_y
false_neg = true_y & ~pred_y
conf_mat = pd.DataFrame([[np.sum(true_pos), np.sum(false_neg)], [np.sum(false_pos), np.sum(true_neg)]],
index=['Y = default', 'Y = paid off'],
columns=['Yhat = default', 'Yhat = paid off'])
print(conf_mat)
print(confusion_matrix(y, logit_reg.predict(X)))
# The package _dmba_ contains the function `classificationSummary` that prints confusion matrix and accuracy for a classification model.
classificationSummary(y, logit_reg.predict(X),
class_names=logit_reg.classes_)
### Precision, Recall, and Specificity
# The _scikit-learn_ function `precision_recall_fscore_support` returns
# precision, recall, fbeta_score and support.
conf_mat = confusion_matrix(y, logit_reg.predict(X))
print('Precision', conf_mat[0, 0] / sum(conf_mat[:, 0]))
print('Recall', conf_mat[0, 0] / sum(conf_mat[0, :]))
print('Specificity', conf_mat[1, 1] / sum(conf_mat[1, :]))
precision_recall_fscore_support(y, logit_reg.predict(X),
labels=['default', 'paid off'])
### ROC Curve
# The function `roc_curve` in _Scikit-learn_ calculates all the information that is required for plotting a ROC curve.
logit_reg = LogisticRegressionCV(penalty="l2",
Cs=100,
solver='liblinear',
cv=10,
class_weight='balanced',
scoring='accuracy',
max_iter=1000)
logit_reg.fit(train_X, train_y)
# In[20]:
# display confusion matrices for train and test data
classificationSummary(train_y, logit_reg.predict(train_X))
classificationSummary(test_y, logit_reg.predict(test_X))
# In[21]:
# display classification report for the test data
classes = logit_reg.predict(test_X)
print(metrics.classification_report(test_y, classes))
# ### Build a default RandomForest classifier
# In[22]:
# Rerun the same train/test split as before
# Subset a specific set/ predicting for new data
df = pd.concat([
pd.DataFrame({
'actual': y_valid,
'predicted': y_valid_pred
}),
pd.DataFrame(predProb_valid, index=y_valid.index)
],
axis=1)
mask = ((X_valid.inventorygrowthabovefive_YES == 1) &
(X_valid.populationgrowthabove_YES == 1))
print(df[mask])
#Confusionmatrix
classificationSummary(y_train, y_train_pred, class_names=classes)
print()
classificationSummary(y_valid, y_valid_pred, class_names=classes)
# In[47]:
#Regressiontree
get_ipython().run_line_magic('matplotlib', 'inline')
from pathlib import Path
import pandas as pd
import numpy as np
