def test_df_to_padded_padded_to_df():
"""Tests df_to_padded, padded_to_df
"""
# Call with names? Call with order?
# Continuous tte?
# Contiguous t?
#
np.random.seed(1)
n_seqs = 100
max_seq_length = 100
ids = xrange(n_seqs)
df = generate_random_df(n_seqs, max_seq_length)
df = df.reset_index(drop=True)
# Column names to transform to tensor
column_names = ['event', 'int_column', 'double_column']
dtypes = df[column_names].dtypes.values
padded = df_to_padded(df, column_names)
df_new = padded_to_df(padded, column_names, dtypes, ids=ids)
column_names = ['id', 't', 'event', 'int_column', 'double_column']
# Pandas is awful. Index changes when slicing
df = df[column_names].reset_index(drop=True)
pd.util.testing.assert_frame_equal(df[column_names], df_new)
def test_align_padded():
np.random.seed(1)
n_seqs = 10
max_seq_length = 10
df = generate_random_df(n_seqs, max_seq_length)
column_names = ['event', 'int_column', 'double_column']
padded = df_to_padded(df, column_names)
np.testing.assert_array_equal(
padded, left_pad_to_right_pad(right_pad_to_left_pad(padded)))
padded = np.copy(np.squeeze(padded))
np.testing.assert_array_equal(
padded, left_pad_to_right_pad(right_pad_to_left_pad(padded)))
def test_align_padded():
"""test the function for switching between left-right padd.
"""
# For simplicity, create a realistic padded tensor
np.random.seed(1)
n_seqs = 10
max_seq_length = 10
df = generate_random_df(n_seqs, max_seq_length)
cols_to_expand = ['event', 'int_column', 'double_column']
padded = df_to_padded(df, cols_to_expand, 'id', 't_elapsed')
np.testing.assert_array_equal(
padded, left_pad_to_right_pad(right_pad_to_left_pad(padded)))
padded = np.copy(np.squeeze(padded))
np.testing.assert_array_equal(
padded, left_pad_to_right_pad(right_pad_to_left_pad(padded)))
def df_to_padded_padded_to_df_runner(t_col):
n_seqs = 5
max_seq_length = 10
ids = xrange(n_seqs)
cols_to_expand = ['event', 'int_column', 'double_column']
np.random.seed(1)
df = generate_random_df(n_seqs, max_seq_length)
df = df.reset_index(drop=True)
# Column names to transform to tensor
dtypes = df[cols_to_expand].dtypes.values
padded = df_to_padded(df, cols_to_expand, 'id', t_col)
df_new = padded_to_df(padded, cols_to_expand, dtypes, ids, 'id', t_col)
# Pandas is awful. Index changes when slicing
df = df[['id', t_col] + cols_to_expand].reset_index(drop=True)
pd.util.testing.assert_frame_equal(df, df_new)
def test_df_to_padded_padded_to_df():
"""Tests df_to_padded, padded_to_df
"""
# Call with names? Call with order?
# Continuous tte?
# Contiguous t?
#
np.random.seed(1)
n_seqs = 100
max_seq_length = 100
ids = xrange(n_seqs)
df = generate_random_df(n_seqs, max_seq_length)
column_names = ['event', 'int_column', 'double_column']
dtypes = ['double', 'int', 'float']
padded = df_to_padded(df, column_names)
df_new = padded_to_df(padded, column_names, dtypes, ids=ids)
assert False not in (
df[['id', 't', 'event', 'int_column', 'double_column']].values == df_new.values)[0],\
'test_df_to_padded_padded_to_df failed'