import warnings
import numpy as np
import pandas as pd
import pytest
from sklearn.metrics import f1_score, mean_squared_error
from datawig.column_encoders import BowEncoder
from datawig.mxnet_input_symbols import BowFeaturizer
from datawig.simple_imputer import SimpleImputer
from datawig.utils import logger, rand_string, random_split, generate_df_numeric, generate_df_string
from datawig import column_encoders
warnings.filterwarnings("ignore")
logger.setLevel("INFO")
def test_simple_imputer_no_string_column_name():
with pytest.raises(ValueError):
SimpleImputer([0], '1')
with pytest.raises(ValueError):
SimpleImputer(['0'], 1)
def test_simple_imputer_real_data_default_args(test_dir, data_frame):
"""
Tests SimpleImputer with default options
"""
feature_col = "string_feature"
# permissions and limitations under the License.
"""
DataWig tests for explaining predictions
"""
import os
import datawig
from datawig.utils import random_split
from datawig.utils import logger
import pandas as pd
import numpy as np
from sklearn.metrics import precision_score
from datawig import Imputer
logger.setLevel("DEBUG")
def test_explain_method_synthetic(test_dir):
# Generate simulated data for testing explain method
# Predict output column with entries in ['foo', 'bar'] from two columns, one
# categorical in ['foo', 'dummy'], one text in ['text_foo_text', 'text_dummy_text'].
# the output column is deterministically 'foo', if 'foo' occurs anywhere in any input column.
N = 100
cat_in_col = ['foo' if r > (1 / 2) else 'dummy' for r in np.random.rand(N)]
text_in_col = ['fff' if r > (1 / 2) else 'ddd' for r in np.random.rand(N)]
hash_in_col = ['h' for r in range(N)]
cat_out_col = [
'foo' if 'f' in input[0] + input[1] else 'bar'
for input in zip(cat_in_col, text_in_col)