def main():
markdown = PagedownToHtml()
print("Reading the private leaderboard file")
test = data_io.get_test_df()
for i in test.index:
test["BodyMarkdown"][i] = markdown.convert(test["BodyMarkdown"][i])
print("Loading the trained model")
classifier = data_io.load_model("model.pickle")
print("Making predictions")
probs = classifier.predict_proba(test)
solution = data_io.get_private_leaderboard_solution_df()
print("Open AUC: %0.6f" % metrics.auc(solution["open"], probs[:,1]))
def main():
print("Loading the test data")
classifier = data_io.load_model()
print ("Load test data. And Clean..")
test = data_io.get_test_df()
test = FeatureConverter().clean_data(test)
passengerIds = test['Id']
test.drop(['Id'], axis = 1, inplace = True)
test = test.values
print("Making predictions")
predictions = classifier.predict(test).astype(int)
#predictions = predictions.reshape(len(predictions), 1)
print("Writing predictions to file")
data_io.write_submission(predictions, passengerIds, ['Id', 'Cover_Type'])
def main():
print("Loading the test data")
classifier = data_io.load_model()
print("Load test data. And Clean..")
test = data_io.get_test_df()
test = FeatureConverter().clean_data(test)
passengerIds = test['Id']
test.drop(['Id'], axis=1, inplace=True)
test = test.values
print("Making predictions")
predictions = classifier.predict(test).astype(int)
#predictions = predictions.reshape(len(predictions), 1)
print("Writing predictions to file")
data_io.write_submission(predictions, passengerIds, ['Id', 'Cover_Type'])
def main():
print("Reading in the raw data of features and salaries for merging")
train_f = data_io.get_train_f_df()
train_s = data_io.get_train_s_df()
#train_f: training feature data; train_s: training salary data with 0 items deleted
"""
train_f.describe
train_s.describe
"""
#merge the data by jobId, similar to SQL join
data = pd.merge(train_f,train_s,how='left')
data.to_csv("D:/job/indeed_data_science_exercise/RFC1/train9merge2.csv", sep=',',encoding='utf-8')
# seperate the data into features set of the feature columns and the set with target column salary only
#'companyId' excluded
characters = ["jobType", "degree", "major", "industry", "yearsExperience", "milesFromMetropolis"]
x = data[characters]
y = data[['salary']]
print("Extracting features and training model")
classifier = get_pipeline()
classifier.fit(xtr, ytr)
print("Saving the classifier")
data_io.save_model(classifier)
print("Load testing data")
testin = data_io.get_test_df()
test=testin[characters]
print("Making predictions")
predictions = classifier.predict(test)
predictions = predictions.reshape(len(predictions), 1)
#classifier.get_params
#pred_score=explained_variance_score(ycv, predictions, multioutput='raw_values')
print("Writing predictions to file")
write_submission(predictions)