predictive_analytics1.py

print(basetable.head())
# Assign the number of rows in the basetable to the variable 'population_size'.
population_size  = len(basetable)
# Print the population size.
print(population_size)
# Assign the number of targets to the variable 'targets_count'.
targets_count = sum(basetable["target"])
# Print the number of targets.
print(targets_count)
# Print the incidence, i.e. the number of targets divided by the population size.
print(targets_count/population_size)

# Count and print the number of females.
print(sum(basetable["gender"]== 'F'))
# Count and print the number of males.
print(sum(basetable["gender"]== 'M'))

from sklearn import linear_model
# Create a dataframe X that only contains the candidate predictors age, gender_F and time_since_last_gift.
X = basetable[["age", "gender_F", "time_since_last_gift"]]
# Create a dataframe Y that contains the target.
Y = basetable[["target"]]
# Create a logistic regression model logreg and fit it to the data.
logreg = linear_model.LogisticRegression()
logreg.fit(X, Y)

coef = logreg.coef_
# Assign the intercept to the variable intercept
intercept = logreg.intercept_
# Print coef and intercept
print(coef)
print(intercept)

new_data = current_data[["age","gender_F","time_since_last_gift"]]
# Make a prediction for each observation in new_data and assign it to predictions
predictions = logreg.predict_proba(new_data)

predictions_sorted = predictions.sort(["probability"])
# Print the row of predictions_sorted that has the donor that is most likely to donate
print(predictions_sorted.tail(1))