def test_predict(root, rows_csv, encoding, **unused):
COUNT = 10
with tempdir(cleanup_on_error=CLEANUP_ON_ERROR):
with loom.query.get_server(root, debug=True) as query_server:
result_out = 'predictions_out.csv'
rows_in = os.listdir(rows_csv)[0]
rows_in = os.path.join(rows_csv, rows_in)
encoders = json_load(encoding)
name_to_encoder = {e['name']: load_encoder(e) for e in encoders}
preql = loom.preql.PreQL(query_server, encoding)
preql.predict(rows_in, COUNT, result_out, id_offset=False)
with open_compressed(rows_in, 'rb') as fin:
with open(result_out, 'r') as fout:
in_reader = csv.reader(fin)
out_reader = csv.reader(fout)
fnames = in_reader.next()
out_reader.next()
for in_row in in_reader:
for i in range(COUNT):
out_row = out_reader.next()
bundle = zip(fnames, in_row, out_row)
for name, in_val, out_val in bundle:
encode = name_to_encoder[name]
observed = bool(in_val.strip())
if observed:
assert_almost_equal(
encode(in_val),
encode(out_val))
else:
assert_true(bool(out_val.strip()))
def test_predict(root, rows_csv, encoding, **unused):
with tempdir(cleanup_on_error=CLEANUP_ON_ERROR):
with loom.preql.get_server(root, debug=True) as preql:
result_out = 'predictions_out.csv'
rows_in = os.listdir(rows_csv)[0]
rows_in = os.path.join(rows_csv, rows_in)
preql.predict(rows_in, COUNT, result_out, id_offset=True)
print 'DEBUG', open_compressed(rows_in).read()
print 'DEBUG', open_compressed(result_out).read()
_check_predictions(rows_in, result_out, encoding)
def test_predict(root, rows_csv, encoding, **unused):
with tempdir(cleanup_on_error=CLEANUP_ON_ERROR):
with loom.preql.get_server(root, debug=True) as preql:
result_out = 'predictions_out.csv'
rows_in = os.listdir(rows_csv)[0]
rows_in = os.path.join(rows_csv, rows_in)
preql.predict(rows_in, COUNT, result_out, id_offset=True)
print 'DEBUG', open_compressed(rows_in).read()
print 'DEBUG', open_compressed(result_out).read()
_check_predictions(rows_in, result_out, encoding)
def test_predict_pandas(root, rows_csv, schema, **unused):
feature_count = len(json_load(schema))
with loom.preql.get_server(root, debug=True) as preql:
rows_filename = os.path.join(rows_csv, os.listdir(rows_csv)[0])
with open_compressed(rows_filename) as f:
rows_df = pandas.read_csv(f,
converters=preql.converters,
index_col='_id')
print 'rows_df ='
print rows_df
row_count = rows_df.shape[0]
assert_equal(rows_df.shape[1], feature_count)
rows_io = StringIO(rows_df.to_csv())
result_string = preql.predict(rows_io, COUNT, id_offset=True)
result_df = pandas.read_csv(StringIO(result_string), index_col=False)
print 'result_df ='
print result_df
assert_equal(result_df.ndim, 2)
assert_equal(result_df.shape[0], row_count * COUNT)
assert_equal(result_df.shape[1], 1 + feature_count)
def test_predict_pandas(root, rows_csv, schema, **unused):
feature_count = len(json_load(schema))
with loom.preql.get_server(root, debug=True) as preql:
rows_filename = os.path.join(rows_csv, os.listdir(rows_csv)[0])
with open_compressed(rows_filename) as f:
rows_df = pandas.read_csv(
f,
converters=preql.converters,
index_col='_id')
print 'rows_df ='
print rows_df
row_count = rows_df.shape[0]
assert_equal(rows_df.shape[1], feature_count)
rows_io = StringIO(rows_df.to_csv())
result_string = preql.predict(rows_io, COUNT, id_offset=True)
result_df = pandas.read_csv(StringIO(result_string), index_col=False)
print 'result_df ='
print result_df
assert_equal(result_df.ndim, 2)
assert_equal(result_df.shape[0], row_count * COUNT)
assert_equal(result_df.shape[1], 1 + feature_count)
