def test_data_health_check(self):
self.assertDictEqual(d1={
'cases': [],
'features': ['J', 'K']
},
d2=DataExplorer(df=DATA_SET,
plot=False).data_health_check())
def test_data_distribution(self):
_data_distribution: dict = DataExplorer(
df=DATA_SET, plot=False).data_distribution()
_sample_results: dict = dict(F=_data_distribution['F'].get('Hamburg'),
C=_data_distribution['C'].get('mean'))
self.assertDictEqual(d1=dict(F=4, C=0.49000000000000005),
d2=_sample_results)
def test_get_feature_types(self):
self.assertDictEqual(d1={
'continuous': ['C', 'G', 'H'],
'categorical': ['A', 'B', 'F', 'I', 'J', 'K'],
'ordinal': [],
'date': ['D'],
'text': ['E']
},
d2=DataExplorer(df=DATA_SET,
plot=False).get_feature_types())
def test_data_typing(self):
self.assertDictEqual(d1={
'B': 'int',
'D': 'datetime',
'F': 'int',
'I': 'int',
'J': 'int',
'K': 'int'
},
d2=DataExplorer(df=DATA_SET,
plot=False).data_typing())
import pandas as pd
import unittest
from easyexplore.data_explorer import DataExplorer
from easyexplore.text_miner import TextMiner
DATA_SET: pd.DataFrame = pd.read_csv(
filepath_or_buffer='amazon_musical_instruments_reviews.csv')
ID_TEXT: dict = DataExplorer(df=DATA_SET).get_feature_types()
TEXT_MINER: TextMiner = TextMiner(df=DATA_SET,
features=ID_TEXT.get('id_text'),
lang='en',
auto_interpret_natural_language=True)
class TextMinerTest(unittest.TestCase):
"""
Unit test for class TextMiner
"""
def test_clustering(self):
pass
def test_detect_lang(self):
_lang_feature: int = len(
TEXT_MINER.get_str_match(cases=list(TEXT_MINER.df.keys()),
substring='_lang'))
TEXT_MINER.detect_lang(sampling=True)
self.assertTrue(expr=_lang_feature == 0 and len(
TEXT_MINER.get_str_match(cases=list(TEXT_MINER.df.keys()),
substring='_lang')) > 0)
def test_text_analyzer(self):
self.assertTrue(expr=DataExplorer(df=TEXT_DATA).text_analyzer(
lang='en').shape[1] > 0)
def test_break_down(self):
self.assertEqual(first=0.49000000000000005,
second=DataExplorer(df=DATA_SET,
plot=False).break_down()
['continuous']['J']['de']['C'].get('mean'))