def read_dataset(is_merged):
debug = DEBUG
if debug:
filename_train = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'train_translated', debug)
filename_test = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'test_translated', debug)
else:
filename_train = '../input/{}.feather'.format('train_translated')
filename_test = '../input/{}.feather'.format('test_translated')
print_doing('reading train, test and merge')
if is_merged:
df = read_train_test(filename_train,
filename_test,
'.feather',
is_merged=True)
if debug: print(df.head())
else:
train_df, test_df = read_train_test(filename_train,
filename_test,
'.feather',
is_merged=False)
if debug:
print(train_df.head())
print(test_df.head())
print_memory()
if is_merged:
return df
else:
return train_df, test_df
def read_dataset_origin(dataset):
filename_train = '../input/train.csv'
filename_test = '../input/test.csv'
print_doing('reading train, test and merge')
df = read_train_test(filename_train,
filename_test,
'.feather',
is_merged=1)
print_memory()
print(df.head())
return df
def read_dataset():
debug = DEBUG
if debug:
filename_train = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'train', debug)
filename_test = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'test', debug)
else:
filename_train = '../input/{}.feather'.format('train')
filename_test = '../input/{}.feather'.format('test')
print_doing('reading train, test and merge')
df = read_train_test(filename_train,
filename_test,
'.feather',
is_merged=1)
print_memory()
print(df.head())
return df
def read_dataset_deal_probability(seed):
debug = DEBUG
if debug:
filename_train = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'train', debug)
filename_test = '../input/debug{}/{}_debug{}.feather'.format(
debug, 'test', debug)
else:
filename_train = '../input/{}.feather'.format('train')
filename_test = '../input/{}.feather'.format('test')
print_doing('reading train, test and merge')
train_df, test_df = read_train_test(filename_train,
filename_test,
'.feather',
is_merged=0)
df = find_df_local_valid_and_make_deal_prob_nan(train_df, test_df, seed)
print_memory()
print(df.head())
return df