def train_run():
l_reg = XGBClassifier(seed=27, silent=False, verbose_eval=True, subsample=0.8, reg_lambda=5.0, n_estimators=800, min_child_weight=1, max_depth=15,
learning_rate=0.03, gamma=0.5, colsample_bytree=0.9, colsample_bylevel=0.7)
file_path = os.path.join(os.getcwd(), 'input_data/train_amex/train.csv')
data = pd.read_csv(file_path)
data, y_hat, scaler, pca = data_cleaner_train(data)
data.loc[:, 'yhat'] = y_hat
d1 = data.loc[data.yhat == 1, :]
d2 = data.loc[data.yhat == 0, :]
data_op = pd.DataFrame()
for i in range(3):
print(i)
d1_sample = d1.sample(frac=1)
d2_sample = d2.sample(n=len(d1_sample), replace=False)
data_tmp = d1_sample.append(d2_sample)
data_op = data_op.append(data_tmp, ignore_index=True)
data_op = data_op.sample(frac=1)
yhat_op = data_op.loc[:, 'yhat']
data_op.drop('yhat', axis=1, inplace=True)
data.drop('yhat', axis=1, inplace=True)
# # specify parameters and distributions to sample from
# one_to_left = st.beta(10, 1)
# from_zero_positive = st.expon(0, 50)
#
# param_dist = {
# 'silent': [False],
# 'max_depth': [15, 10,15],
# 'learning_rate': [0.03, 0.05, 0.1],
# 'subsample': [0.7, 0.8, 0.9, 1.0],
# 'colsample_bytree': [0.7, 0.8, 0.9],
# 'colsample_bylevel': [0.7, 0.8, 0.9],
# 'min_child_weight': [0.5, 1.0, 3.0, 7.0, 10.0],
# 'gamma': [0.25, 0.5, 1.0],
# 'reg_lambda': [0.1, 1.0, 5.0, 10.0, 50.0],
# 'n_estimators': [200, 500, 800]}
#
# # run randomized search
# n_iter_search = 10
# random_search = RandomizedSearchCV(l_reg, param_distributions=param_dist,
# n_iter=n_iter_search, cv=3, scoring='roc_auc', n_jobs=3)
#
# model = random_search.fit(data_op.values, yhat_op.values)
# report(random_search.cv_results_)
model = l_reg.fit(data_op.values, yhat_op.values)
output = model.predict(data.values)
roc = roc_auc_score(y_hat.values, output)
print('#############################################################')
print(roc)
joblib.dump(pca, pca_file_name)
joblib.dump(model, model_filename)
joblib.dump(scaler, scaler_filename)
def train_run():
l_reg = RandomForestClassifier(random_state=0, n_jobs=3, verbose=3)
file_path = os.path.join(os.getcwd(), 'input_data/train_amex/train.csv')
data = pd.read_csv(file_path)
data, y_hat, scaler = data_cleaner_train(data)
data.loc[:, 'yhat'] = y_hat
d1 = data.loc[data.yhat == 1, :]
d2 = data.loc[data.yhat == 0, :]
data_op = pd.DataFrame()
for i in range(5):
print(i)
d1_sample = d1.sample(frac=1, replace=False)
d2_sample = d2.sample(n=len(d1_sample), replace=False)
data_tmp = d1_sample.append(d2_sample)
data_op = data_op.append(data_tmp, ignore_index=True)
data_op = data_op.sample(frac=1)
yhat_op = data_op.loc[:, 'yhat']
# predictors = list(data_op.drop('yhat', axis=1).columns)
# modelfit(l_reg, data_op, predictors, performCV=True, printFeatureImportance=True, cv_folds=5)
data_op.drop('yhat', axis=1, inplace=True)
data.drop('yhat', axis=1, inplace=True)
# specify parameters and distributions to sample from
param_dist = {
"max_depth": [3, 10, 20, 30, 40, 50],
"max_features": sp_randint(5, 50),
"min_samples_split": sp_randint(2, 20),
"bootstrap": [True, False],
"criterion": ["gini", "entropy"]
}
# run randomized search
n_iter_search = 10
random_search = RandomizedSearchCV(l_reg,
param_distributions=param_dist,
n_iter=n_iter_search,
cv=5,
scoring='roc_auc',
n_jobs=1)
model = random_search.fit(data_op.values, yhat_op.values)
report(random_search.cv_results_)
# model = l_reg.fit(data_op.values, yhat_op.values)
output = model.predict(data.values)
roc = roc_auc_score(y_hat.values, output)
print(roc)
joblib.dump(model, model_filename)
joblib.dump(scaler, scaler_filename)
def train_run():
l_reg = GradientBoostingClassifier(max_features=None,
subsample=0.80,
random_state=0,
verbose=True,
learning_rate=0.05,
n_estimators=200,
min_samples_split=500,
min_samples_leaf=500,
max_depth=15)
file_path = os.path.join(os.getcwd(), 'input_data/train_amex/train.csv')
data = pd.read_csv(file_path)
data, y_hat, scaler, pca = data_cleaner_train(data)
data.loc[:, 'yhat'] = y_hat
d1 = data.loc[data.yhat == 1, :]
d2 = data.loc[data.yhat == 0, :]
data_op = pd.DataFrame()
for i in range(1):
print(i)
d1_sample = d1.sample(frac=1)
d2_sample = d2.sample(n=len(d1_sample), replace=False)
data_tmp = d1_sample.append(d2_sample)
data_op = data_op.append(data_tmp, ignore_index=True)
data_op = data_op.sample(frac=1)
yhat_op = data_op.loc[:, 'yhat']
data_op.drop('yhat', axis=1, inplace=True)
data.drop('yhat', axis=1, inplace=True)
# # specify parameters and distributions to sample from
# param_dist = {'max_depth': range(10, 30,5), 'min_samples_split': range(100, 1000, 200), 'n_estimators': range(100, 1000, 300), 'min_samples_leaf': range(100, 1000, 200)}
#
# # run randomized search
# n_iter_search = 10
# random_search = RandomizedSearchCV(l_reg, param_distributions=param_dist,
# n_iter=n_iter_search, cv=3, scoring='roc_auc', n_jobs=3)
#
# model = random_search.fit(data_op.values, yhat_op.values)
# report(random_search.cv_results_)
model = l_reg.fit(data_op.values, yhat_op.values)
output = model.predict(data.values)
roc = roc_auc_score(y_hat.values, output)
print('#############################################################')
print(roc)
joblib.dump(pca, pca_file_name)
joblib.dump(model, model_filename)
joblib.dump(scaler, scaler_filename)
def train_run():
l_reg = RandomForestClassifier(n_estimators=500,
max_depth=30,
random_state=0,
n_jobs=7,
verbose=2)
file_path = os.path.join(os.getcwd(), 'input_data/train_amex/train.csv')
userlogs_path = os.path.join(
os.getcwd(), 'input_data/train_amex/historical_user_logs.csv')
data = pd.read_csv(file_path)
userlogs = pd.read_csv(userlogs_path)
data, y_hat, scaler, to_keep_prod_2, is_interesting = data_cleaner_train(
data, userlogs)
with open(to_keep_file_name, 'wb') as f:
pickle.dump(to_keep_prod_2, f)
is_interesting.to_pickle(is_int_fname)
data.loc[:, 'yhat'] = y_hat
d1 = data.loc[data.yhat == 1, :]
d2 = data.loc[data.yhat == 0, :]
data_op = pd.DataFrame()
yhat_op = pd.DataFrame()
for i in range(50):
print(i)
d1_sample = d1.sample(n=10000, replace=True)
d2_sample = d2.sample(n=len(d1_sample), replace=True)
data_tmp = d1_sample.append(d2_sample)
data_op = data_op.append(data_tmp, ignore_index=True)
yhat_op = data_op.loc[:, 'yhat']
data_op.drop('yhat', axis=1, inplace=True)
data.drop('yhat', axis=1, inplace=True)
data = data.sample(frac=1)
model = l_reg.fit(data_op.values, yhat_op.values)
output = model.predict(data.values)
# output[output > 0.5] = 1
# output[output < 0.5] = 0
roc = roc_auc_score(y_hat.values, output)
print(roc)
joblib.dump(model, model_filename)
joblib.dump(scaler, scaler_filename)