def main():
print("Reading the test data")
test = data_io.read_test()
print("Reading in the meta data")
paper_author, paper_author_indexed = f.get_paper_author()
print("Computing Relational Information")
computed_features = f.get_all_computed_features(paper_author)
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
predictions = []
for author_id, row in test.iterrows():
features = []
paper_ids = []
for paper_id in row["PaperIds"]:
s = f.get_features(paper_id, author_id, paper_author_indexed,
computed_features)
if s is None:
print("Error at Author Id %d And Paper Id %d" %
(author_id, paper_id))
else:
features.append(s)
paper_ids.append(paper_id)
feature_matrix = pd.DataFrame(features)
preds = classifier.predict_proba(feature_matrix)[:, 1]
paper_ids_sorted = sorted(zip(preds, row["PaperIds"]), reverse=True)
print(paper_ids_sorted)
predictions.append([x[1] for x in paper_ids_sorted])
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Reading the test data")
test = data_io.read_test()
print("Reading in the meta data")
paper_author, paper_author_indexed = f.get_paper_author()
print("Computing Relational Information")
computed_features = f.get_all_computed_features(paper_author)
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
predictions = []
for author_id, row in test.iterrows():
features = []
paper_ids = []
for paper_id in row["PaperIds"]:
s = f.get_features(paper_id, author_id, paper_author_indexed,computed_features)
if s is None:
print("Error at Author Id %d And Paper Id %d" % (author_id, paper_id))
else:
features.append(s)
paper_ids.append(paper_id)
feature_matrix = pd.DataFrame(features)
preds = classifier.predict_proba(feature_matrix)[:,1]
paper_ids_sorted = sorted(zip(preds,row["PaperIds"]), reverse=True)
print(paper_ids_sorted)
predictions.append([x[1] for x in paper_ids_sorted])
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Reading the test data")
test = data_io.read_test()
print("Making predictions")
np.random.seed(12341234)
predictions = test.apply(shuffle, axis=1)
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Reading test data")
test = data_io.read_test()
ordinals = np.arange(len(test))
recommendations = zip(test["srch_id"], test["prop_id"], ordinals)
print("Writing predictions to file")
data_io.write_submission(recommendations, "testOrderBenchmark.csv")
def main():
print("Reading test data")
test = data_io.read_test()
ordinals = np.arange(len(test))
recommendations = zip(test["srch_id"], test["prop_id"], ordinals)
print("Writing predictions to file")
data_io.write_submission(recommendations, "testOrderBenchmark.csv")
def __init__(self):
self.train = data_io.read_train()
self.test = data_io.read_test()
self.destin = data_io.read_desin()
# pca analysis on the destination
pca = PCA(n_components=3)
self.dest_pca = pca.fit_transform(
self.destin[["d{0}".format(i + 1) for i in range(149)]])
self.dest_pca = pd.DataFrame(self.dest_pca)
self.dest_pca["srch_destination_id"] = self.destin[
"srch_destination_id"]
def main():
test = data_io.read_test()
## deal with the NAs, and add features
train.feature_eng(test)
## predict the booking_bool
print("Loading the Booking classifier..")
tstart = datetime.now()
classifier = data_io.load_model(True)
print("Time used,")
print(datetime.now() - tstart)
print("Making predictions on the booking_bool..")
tstart = datetime.now()
b_fnames = train.get_features(test, True)
b_test_f = test[b_fnames].values
b_prob = classifier.predict_proba(b_test_f)[:, 1]
b_prob = list(-1.0 * b_prob)
print("Time used,")
print(datetime.now() - tstart)
## predict the click_bool
print("Loading the Click classifier..")
tstart = datetime.now()
classifier = data_io.load_model(False)
print("Time used,")
print(datetime.now() - tstart)
print("Making predictions on the click_bool..")
tstart = datetime.now()
c_fnames = train.get_features(test, False)
c_test_f = test[c_fnames].values
c_prob = classifier.predict_proba(c_test_f)[:, 1]
c_prob = list(-1.0 * c_prob)
print("Time used,")
print(datetime.now() - tstart)
## Making Recommendations
recommendations = zip(test["srch_id"], test["prop_id"],
4 * b_prob + c_prob)
print("Writing predictions to file..")
tstart = datetime.now()
data_io.write_submission(recommendations)
print("Time used,")
print(datetime.now() - tstart)
def main():
test = data_io.read_test()
## deal with the NAs, and add features
train.feature_eng(test)
## predict the booking_bool
print("Loading the Booking classifier..")
tstart = datetime.now()
classifier = data_io.load_model(True)
print("Time used,")
print datetime.now() - tstart
print("Making predictions on the booking_bool..")
tstart = datetime.now()
b_fnames = train.get_features(test, True)
b_test_f = test[b_fnames].values
b_prob = classifier.predict_proba(b_test_f)[:,1]
b_prob = list(-1.0*b_prob)
print("Time used,")
print datetime.now() - tstart
## predict the click_bool
print("Loading the Click classifier..")
tstart = datetime.now()
classifier = data_io.load_model(False)
print("Time used,")
print datetime.now() - tstart
print("Making predictions on the click_bool..")
tstart = datetime.now()
c_fnames = train.get_features(test, False)
c_test_f = test[c_fnames].values
c_prob = classifier.predict_proba(c_test_f)[:,1]
c_prob = list(-1.0*c_prob)
print("Time used,")
print datetime.now() - tstart
## Making Recommendations
recommendations = zip(test["srch_id"], test["prop_id"], 4*b_prob+c_prob)
print("Writing predictions to file..")
tstart = datetime.now()
data_io.write_submission(recommendations)
print("Time used,")
print datetime.now() - tstart
def main():
print("Reading test data ...")
test = data_io.read_test()
test.fillna(0, inplace=True)
feature_names = list(test.columns)
feature_names.remove("date_time")
features = test[feature_names].values
print("Loading the Regressor ...")
regressor = data_io.load_model()
print("Making predictions ...")
predictions = regressor.predict(features)
predictions = list(-1.0*predictions)
recommendations = zip(test["srch_id"], test["prop_id"], predictions)
print("Writing predictions to file ...")
data_io.write_submission(recommendations)
def main():
print("Reading test data")
test = data_io.read_test()
test.fillna(0, inplace=True)
feature_names = list(test.columns)
feature_names.remove("date_time")
features = test[feature_names].values
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
predictions = classifier.predict_proba(features)[:, 1]
predictions = list(-1.0 * predictions)
recommendations = zip(test["srch_id"], test["prop_id"], predictions)
print("Writing predictions to file")
data_io.write_submission(recommendations)
def prediction(n_train_samples):
proc_test_samples_file = get_paths()["proc_test_samples_path"]
if os.path.exists(proc_test_samples_file):
print "Loading processed test data..."
new_test_samples = pd.read_csv(proc_test_samples_file)
else:
print "Reading test data..."
test_samples = data_io.read_test()
test_samples = test_samples.fillna(value=0)
print "Porcessing test samples"
new_test_samples = process_test_samples(test_samples)
new_test_samples.to_csv(proc_test_samples_file, index=None)
test_feature = new_test_samples.values
print "Loading the Random Forest Classifier"
rf_classifier = data_io.load_model(model_name="rf_classifier.pkl")
print "Random Forest Predicting"
rf_predictions = rf_classifier.predict_proba(test_feature)[:, 1]
print "Loading the Gradient Boosting Classifier"
gb_classifier = data_io.load_model(model_name="gb_classifier.pkl")
print "Gradient Boosting Predicting"
gb_predictions = gb_classifier.predict_proba(test_feature)[:, 1]
print "Loading the SGD Classifier"
sgd_classifier = data_io.load_model(model_name="sgd_classifier.pkl")
print "SGD Predicting"
sgd_predictions = sgd_classifier.predict_proba(test_feature)[:, 1]
prob_arr = np.vstack((rf_predictions, gb_predictions, sgd_predictions))
mean_score = np.mean(prob_arr, axis=0)
mean_score = -1.0 * mean_score
mean_recommendations = zip(new_test_samples["srch_id"], new_test_samples["prod_id"], mean_score)
print "Writing predictions to file"
data_io.write_submission(mean_recommendations, submission_file="mean_result_%i.csv" % n_train_samples)
srch_length_of_stay_features.SrchLengthOfStayFeatures(self.X),
srch_booking_window_features.SrchBookingWindowFeatures(self.X),
]
return map(self.transformer, feature_list)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Generate features using train/test data")
parser.add_argument("--test", action="store_true", default=False, help="Weather to use test data", required=False)
result = parser.parse_args()
if result.test:
print("Reading test data")
data = data_io.read_test()
else:
print("Reading training data")
data = data_io.read_train()
fm = FeatureExtractor(data)
derived_features = fm.feature_extractor()
data.fillna(0, inplace=True)
data = pandas.concat([data] + derived_features, axis=1)
if result.test:
data_io.save_test_features(data)
else:
data_io.save_train_features(data)
def main():
class bcolors:
HEADER = '\033[95m'
OKBLUE = '\033[94m'
OKGREEN = '\033[92m'
WARNING = '\033[93m'
FAIL = '\033[91m'
ENDC = '\033[0m'
BOLD = '\033[1m'
UNDERLINE = '\033[4m'
print bcolors.HEADER + "Start Training" + bcolors.HEADER
print bcolors.OKBLUE + "Reading and making Trainingset" + bcolors.OKBLUE
train = data_io.read_train()
train.fillna(0, inplace=True)
train_sample = train[:1250000].fillna(value=0) # change the samplesize over here
# list of features that can be removed if you want
feature_names = list(train_sample.columns)
feature_names.remove("click_bool")
feature_names.remove("booking_bool")
feature_names.remove("gross_bookings_usd")
feature_names.remove("date_time")
feature_names.remove("position")
features = train_sample[feature_names].values
target = train_sample["booking_bool"].values
print bcolors.OKGREEN + "Training Dataset" + bcolors.OKGREEN
# check over here , you can find the algorithms at http://scikit-learn.org/stable/modules/ensemble.html
# random forest
classifier = RandomForestClassifier(n_estimators=3200, verbose=2,n_jobs=-1,min_samples_split=10,random_state=1)
# extra Trees (better then random forest) (best till now!)
#classifier = ExtraTreesClassifier(n_estimators=300, verbose=2, n_jobs=-1, min_samples_split=10,random_state=1)
# Adaboost
#classifier = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2),n_estimators=600,learning_rate=1)
# Knearest neighbour with bagging
#classifier = BaggingClassifier(KNeighborsClassifier(), max_samples=0.5, max_features=0.5)
# Gradient Boosting BEST SOLUTION (i suppose,will try tomorrow)
# classifier = GradientBoostingClassifier(loss='deviance', learning_rate=0.1, n_estimators=100, subsample=1.0, min_samples_split=2, min_samples_leaf=1, max_depth=3, init=None, random_state=None, max_features=None, verbose=0)
classifier.fit(features, target)
print bcolors.OKBLUE + "Saving Classifier" + bcolors.OKBLUE
data_io.save_model(classifier)
print bcolors.OKGREEN + "Start Making Predictions On Testset" + bcolors.OKGREEN
print bcolors.OKBLUE + "Reading Testset" + bcolors.OKBLUE
test = data_io.read_test()
test.fillna(0, inplace=True)
feature_names = list(test.columns)
feature_names.remove("date_time")
features = test[feature_names].values
classifier = data_io.load_model()
print bcolors.OKGREEN + "Make Predictions" + bcolors.OKGREEN
predictions = classifier.predict_proba(features)[:,1]
print bcolors.OKBLUE + "Calculate NDcg" + bcolors.OKBLUE
predictions = list(-1.0*predictions)
print bcolors.OKBLUE + "Sort Predictions" + bcolors.OKBLUE
recommendations = zip(test["srch_id"], test["prop_id"], predictions)
print bcolors.OKGREEN + "Writing Predictions To Outputfile" + bcolors.OKGREEN
data_io.write_submission(recommendations)
print ""
print bcolors.ENDC + "Thats all folks,goodbye!" + bcolors.ENDC
def do_prediction(n_trian_samples):
proc_test_samples_file = get_paths()['proc_test_samples_path']
if os.path.exists(proc_test_samples_file):
print "Loading processed test data..."
new_test_samples = pd.read_csv(proc_test_samples_file)
print "Loading processed test data done"
else:
# prediction
print "reading test data..."
test_samples = data_io.read_test()
test_samples = test_samples.fillna(value=0)
print "done."
# process test samples
print "processing test data..."
new_test_samples = process_test_samples(test_samples)
new_test_samples.to_csv(proc_test_samples_file, index=None)
print "Processing test data done."
test_features = new_test_samples.values
# 5.1 random forest prediction
print("Loading the random forest classifier")
rf_classifier = data_io.load_model(model_name='lr_classifier.pkl')
print("random forest Predicting")
# 拿概率值
rf_predictions = rf_classifier.predict_proba(test_features)[:1]
# 5.2 Gradient Boosting prediction
print("Loading the Gradient Boosting classifier")
gb_classifier = data_io.load_model(model_name='gb_classifier.pkl')
print("Gradient Boosting Predicting")
gb_predictions = gb_classifier.predict_proba(test_features)[:1]
# 5.3 SGD prediction
print("Loading the SGD classifier")
sgd_classifier = data_io.load_model(model_name='sgd_classifier.pkl')
print("SGD Predicting")
sgd_predictions = sgd_classifier.predict_proba(test_features)[:1]
# 5.4 LR prediction
# print("Loading the LR classifier")
# lr_classifier = data_io.load_model(model_name='lr_classifier.pkl')
# print("Logistic Regression Predicting")
# lr_predictions = lr_classifier.predict_proba(test_features)[:1]
# step 6 score fusion 把三组概率放到数组中
prob_arr = np.vstack((rf_predictions, gb_predictions, sgd_predictions))
# average mean 取概率的评价值 算术评价
mean_score = np.mean(prob_arr, axis=0)
# for sorting 几何评价，效果不太好
# 前面的排序是升序，乘以-1 改为降序
mean_score = -1.0 * mean_score
# geometric mean
gmean = stats.gmean(prob_arr, axis=0)
# for sorting
gmean = -1.0 * gmean
# step 7 output result
mean_recommendations = zip(new_test_samples['srch_id'],
new_test_samples['prop_id'], mean_score)
gmean_recommendations = zip(new_test_samples['srch_id'],
new_test_samples['prop_id'], gmean)
print("Writing predictions to file")
data_io.write_submission(mean_recommendations, submission_file='mean_result_%i.csv' % n_trian_samples)
data_io.write_submission(gmean_recommendations, submission_file='gmean_result_%i.csv' % n_trian_samples)
