def GCStoLocal(filename):
sshColab.download_to_colab(
project,
bucket_name,
destination_directory='/kaggle/working',
remote_blob_path=f'tps-apr-2021-label/{filename}',
local_file_name=f'{filename}')
return pickle.load(open(f'/kaggle/working/{filename}', 'rb'))
# TODO data.loc[data['Age'].notnull(), 'Age_rg'] = rank_gauss(data.loc[data['Age'].notnull(), 'Age'].values)
# TODO data.loc[data['Fare'].notnull(), 'Fare_rg'] = rank_gauss(data.loc[data['Fare'].notnull(), 'Fare'].values)
#DONE!
os.chdir('/kaggle/working')
pickle.dump(data, open('1parsed_data.pkl', 'wb'))
sshColab.upload_to_gcs(project, bucket_name,
'tps-apr-2021-label/1parsed_data.pkl',
'/kaggle/working/1parsed_data.pkl')
#%%
# ------------------------------------ Age ----------------------------------- #
sshColab.download_to_colab(
project,
bucket_name,
destination_directory='/kaggle/working',
remote_blob_path='tps-apr-2021-label/1parsed_data.pkl',
local_file_name='1parsed_data.pkl')
parsed_data = pickle.load(open('/kaggle/working/1parsed_data.pkl', 'rb'))
data = parsed_data.copy()
data = data.fillna(-1)
the_col = 'Age'
idx_present = data.loc[data[the_col] != -1, :].index.tolist()
idx_missing = data.loc[data[the_col] == -1, :].index.tolist()
data[the_col] = data[the_col].replace(-1, np.nan)
x_train_full = data.loc[idx_present, :].drop(the_col, axis=1)
y_train_full = data.loc[idx_present, :][the_col]
x_test_full = data.loc[idx_missing, :].drop(the_col, axis=1)
cat_features = [
train_df = pd.read_csv(
'/kaggle/input/tabular-playground-series-apr-2021/train.csv')
test_df = pd.read_csv(
'/kaggle/input/tabular-playground-series-apr-2021/test.csv')
train_label = train_df['Survived']
train_id = train_df['PassengerId']
test_id = test_df['PassengerId']
del train_df['Survived'], train_df['PassengerId']
del test_df['PassengerId']
train_rows = train_df.shape[0]
sshColab.download_to_colab(
project,
bucket_name,
destination_directory='/kaggle/working',
remote_blob_path='tps-apr-2021-label/1clean_data.pkl',
local_file_name='1clean_data.pkl')
data = pickle.load(open('/kaggle/working/1clean_data.pkl', 'rb'))
sshColab.download_to_colab(
project,
bucket_name,
destination_directory='/kaggle/working',
remote_blob_path='tps-apr-2021-label/2missing_code_map.pkl',
local_file_name='2missing_code_map.pkl')
missing_code_map = pickle.load(
open('/kaggle/working/2missing_code_map.pkl', 'rb'))
sshColab.download_to_colab(
project,
train_rows = train_df.shape[0]
def timer(start_time=None):
if not start_time:
start_time = datetime.now()
return start_time
elif start_time:
thour, temp_sec = divmod((datetime.now() - start_time).total_seconds(), 3600)
tmin, tsec = divmod(temp_sec, 60)
print('Time taken : %i hours %i minutes and %s seconds.' % (thour, tmin, round(tsec, 2)))
file_to_load = '11dataframe_xgboost_based_trim.pkl'
sshColab.download_to_colab(project, bucket_name,
destination_directory = '/kaggle/working',
remote_blob_path=f'tps-apr-2021-label/{file_to_load}',
local_file_name=file_to_load)
df = pickle.load(open(f'/kaggle/working/{file_to_load}', 'rb'))
file_to_load = '11cols_tuple.pkl'
sshColab.download_to_colab(project, bucket_name,
destination_directory = '/kaggle/working',
remote_blob_path=f'tps-apr-2021-label/{file_to_load}',
local_file_name=file_to_load)
cat_cols, num_cols = pickle.load(open(f'/kaggle/working/{file_to_load}', 'rb'))
def feature_distribution():
plt.figure(figsize=(16, 32))
for i, col in enumerate(df.columns.tolist()):
ax = plt.subplot(10, 2, i + 1)
ax.set_title(col)