Created
September 5, 2019 13:51
-
-
Save smly/367c53e855cdaeea35736f32876b7416 to your computer and use it in GitHub Desktop.
OptunaLGBM
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Python script using data from DonorsChoose.org Application Screening | |
# Forked from https://www.kaggle.com/opanichev/lightgbm-and-tf-idf-starter | |
# Original version: Validation score: 0.7791025740062782 | |
# - Private Score 0.78470 | |
# - Public Score 0.79516 | |
# Tuned version: Validation score: 0.7799395759019241 | |
# - Private Score 0.78622 | |
# - Public Score 0.79535 | |
import gc | |
import json | |
import numpy as np | |
import pandas as pd | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
from sklearn.metrics import roc_auc_score | |
from sklearn.model_selection import RepeatedKFold | |
from sklearn.preprocessing import LabelEncoder | |
from tqdm import tqdm | |
import lightgbm as lgb_original | |
import optuna.integration.lightgbm as lgb | |
# Extract features | |
def extract_features(df): | |
cols = [ | |
'project_title', | |
'project_essay_1', | |
'project_essay_2', | |
'project_essay_3', | |
'project_essay_4', | |
'project_resource_summary', | |
] | |
for col in cols: | |
df[f'{col}_len'] = df[col].apply(lambda x: len(str(x))) | |
df[f'{col}_wc'] = df[col].apply(lambda x: len(str(x).split(' '))) | |
def process_timestamp(df): | |
df['year'] = df['project_submitted_datetime'].apply( | |
lambda x: int(x.split('-')[0])) | |
df['month'] = df['project_submitted_datetime'].apply( | |
lambda x: int(x.split('-')[1])) | |
df['date'] = df['project_submitted_datetime'].apply( | |
lambda x: int(x.split(' ')[0].split('-')[2])) | |
df['day_of_week'] = pd.to_datetime( | |
df['project_submitted_datetime']).dt.weekday | |
df['hour'] = df['project_submitted_datetime'].apply( | |
lambda x: int(x.split(' ')[-1].split(':')[0])) | |
df['minute'] = df['project_submitted_datetime'].apply( | |
lambda x: int(x.split(' ')[-1].split(':')[1])) | |
df['project_submitted_datetime'] = pd.to_datetime( | |
df['project_submitted_datetime']).values.astype(np.int64) | |
def load_features(): | |
# Load Data | |
dtype = { | |
'id': str, | |
'teacher_id': str, | |
'teacher_prefix': str, | |
'school_state': str, | |
'project_submitted_datetime': str, | |
'project_grade_category': str, | |
'project_subject_categories': str, | |
'project_subject_subcategories': str, | |
'project_title': str, | |
'project_essay_1': str, | |
'project_essay_2': str, | |
'project_essay_3': str, | |
'project_essay_4': str, | |
'project_resource_summary': str, | |
'teacher_number_of_previously_posted_projects': int, | |
'project_is_approved': np.uint8, | |
} | |
train = pd.read_csv('train.csv', dtype=dtype, low_memory=True) | |
test = pd.read_csv('test.csv', dtype=dtype, low_memory=True) | |
res = pd.read_csv('resources.csv') | |
# Preprocess data | |
train['project_essay'] = train.apply(lambda row: ' '.join([ | |
str(row['project_essay_1']), | |
str(row['project_essay_2']), | |
str(row['project_essay_3']), | |
str(row['project_essay_4']), | |
]), axis=1) | |
test['project_essay'] = test.apply(lambda row: ' '.join([ | |
str(row['project_essay_1']), | |
str(row['project_essay_2']), | |
str(row['project_essay_3']), | |
str(row['project_essay_4']), | |
]), axis=1) | |
extract_features(train) | |
extract_features(test) | |
drop_cols = [ | |
'project_essay_1', | |
'project_essay_2', | |
'project_essay_3', | |
'project_essay_4', | |
] | |
train.drop(drop_cols, axis=1, inplace=True) | |
test.drop(drop_cols, axis=1, inplace=True) | |
df_all = pd.concat([train, test], axis=0, sort=False) | |
gc.collect() | |
# Merge with resources | |
res = pd.DataFrame(res[['id', 'quantity', 'price']].groupby('id').agg({ | |
'quantity': ['sum', 'min', 'max', 'mean', 'std'], | |
'price': [ | |
'count', 'sum', 'min', 'max', 'mean', 'std', | |
lambda x: len(np.unique(x)), | |
]} | |
)).reset_index() | |
res.columns = ['_'.join(col) for col in res.columns] | |
res.rename(columns={'id_': 'id'}, inplace=True) | |
res['mean_price'] = res['price_sum']/res['quantity_sum'] | |
# res['price_max_to_price_min'] = res['price_max']/res['price_min'] | |
# res['quantity_max_to_quantity_min'] = res['quantity_max']/res['quantity_min'] | |
train = train.merge(res, on='id', how='left') | |
test = test.merge(res, on='id', how='left') | |
del res | |
gc.collect() | |
# Preprocess columns with label encoder | |
print('Label Encoder...') | |
cols = [ | |
'teacher_id', | |
'teacher_prefix', | |
'school_state', | |
'project_grade_category', | |
'project_subject_categories', | |
'project_subject_subcategories' | |
] | |
for c in tqdm(cols): | |
le = LabelEncoder() | |
le.fit(df_all[c].astype(str)) | |
train[c] = le.transform(train[c].astype(str)) | |
test[c] = le.transform(test[c].astype(str)) | |
del le | |
gc.collect() | |
print('Done.') | |
# Preprocess timestamp | |
print('Preprocessing timestamp...') | |
process_timestamp(train) | |
process_timestamp(test) | |
print('Done.') | |
# Preprocess text | |
print('Preprocessing text...') | |
cols_to_vectorize = [ | |
'project_title', | |
'project_essay', | |
'project_resource_summary' | |
] | |
n_features = [400, 4040, 400] | |
for c_i, c in tqdm(enumerate(cols_to_vectorize)): | |
tfidf = TfidfVectorizer( | |
max_features=n_features[c_i], | |
norm='l2', | |
) | |
tfidf.fit(df_all[c]) | |
tfidf_train = np.array(tfidf.transform(train[c]).toarray(), dtype=np.float16) | |
tfidf_test = np.array(tfidf.transform(test[c]).toarray(), dtype=np.float16) | |
for i in range(n_features[c_i]): | |
train[c + '_tfidf_' + str(i)] = tfidf_train[:, i] | |
test[c + '_tfidf_' + str(i)] = tfidf_test[:, i] | |
del tfidf, tfidf_train, tfidf_test | |
gc.collect() | |
print('Done.') | |
del df_all | |
gc.collect() | |
# Prepare data | |
cols_to_drop = [ | |
'id', | |
'teacher_id', | |
'project_title', | |
'project_essay', | |
'project_resource_summary', | |
'project_is_approved', | |
] | |
X = train.drop(cols_to_drop, axis=1, errors='ignore') | |
y = train['project_is_approved'] | |
X_test = test.drop(cols_to_drop, axis=1, errors='ignore') | |
id_test = test['id'].values | |
feature_names = list(X.columns) | |
print(X.shape, X_test.shape) | |
del train, test | |
gc.collect() | |
return X, y, X_test, id_test, feature_names | |
def main(): | |
X, y, X_test, id_test, feature_names = load_features() | |
# Build the model | |
use_first_fold_only = True | |
n_splits = 5 | |
n_repeats = 1 | |
p_buf = [] | |
kf = RepeatedKFold( | |
n_splits=n_splits, | |
n_repeats=n_repeats, | |
random_state=0) | |
auc_buf = [] | |
for fold_idx, (train_index, valid_index) in enumerate(kf.split(X)): | |
print('Fold {}/{}'.format(fold_idx + 1, n_splits)) | |
params = { | |
'objective': 'binary', | |
'metric': 'auc', | |
} | |
lgb_train = lgb.Dataset(X.loc[train_index], | |
y.loc[train_index], | |
feature_name=feature_names) | |
lgb_valid = lgb.Dataset(X.loc[valid_index], | |
y.loc[valid_index]) | |
best_params = {} | |
tuning_history = [] | |
lgb.train( | |
params, | |
lgb_train, | |
num_boost_round=10000, | |
valid_sets=[lgb_train, lgb_valid], | |
early_stopping_rounds=100, | |
best_params=best_params, | |
tuning_history=tuning_history) | |
pd.DataFrame(tuning_history).to_csv('./tuning_history.csv') | |
print('Best parameters: ' + json.dumps(best_params, indent=4)) | |
best_params['learning_rate'] = 0.05 | |
model = lgb_original.train( | |
best_params, | |
lgb_train, | |
num_boost_round=20000, | |
valid_sets=[lgb_train, lgb_valid], | |
early_stopping_rounds=1000, | |
verbose_eval=1000) | |
p = model.predict(X.loc[valid_index], num_iteration=model.best_iteration) | |
auc = roc_auc_score(y.loc[valid_index], p) | |
print('{} AUC: {}'.format(fold_idx, auc)) | |
p = model.predict(X_test, num_iteration=model.best_iteration) | |
if len(p_buf) == 0: | |
p_buf = np.array(p, dtype=np.float16) | |
else: | |
p_buf += np.array(p, dtype=np.float16) | |
auc_buf.append(auc) | |
# Comment this to run several folds | |
if use_first_fold_only: | |
break | |
del model, lgb_train, lgb_valid, p | |
gc.collect | |
auc_mean = np.mean(auc_buf) | |
auc_std = np.std(auc_buf) | |
print('AUC = {:.6f} +/- {:.6f}'.format(auc_mean, auc_std)) | |
preds = p_buf / (fold_idx + 1) | |
# Prepare submission | |
subm = pd.DataFrame() | |
subm['id'] = id_test | |
subm['project_is_approved'] = preds | |
subm.to_csv('submission.csv', index=False) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment