Merge branch 'master' into testing_preprocess

datasets/index.csv

@@ -1,56 +1,56 @@
-Dataset,Data Types,Default Task,Target Variable 1,Target Variable 2,# Instances,# Attributes,Missing Values
-anomaly,Multivariate,Anomaly Detection,None,None,1000,10,N
-france,Multivariate,Association Rule Mining,InvoiceNo,Description,8557,8,N
-germany,Multivariate,Association Rule Mining,InvoiceNo,Description,9495,8,N
-bank,Multivariate,Classification (Binary),deposit,None,45211,17,N
-blood,Multivariate,Classification (Binary),Class,None,748,5,N
-cancer,Multivariate,Classification (Binary),Class,None,683,10,N
-credit,Multivariate,Classification (Binary),default,None,24000,24,N
-diabetes,Multivariate,Classification (Binary),Class variable,None,768,9,N
-electrical_grid,Multivariate,Classification (Binary),stabf,None,10000,14,N
-employee,Multivariate,Classification (Binary),left,None,14999,10,N
-heart,Multivariate,Classification (Binary),DEATH,None,200,16,N
-heart_disease,Multivariate,Classification (Binary),Disease,None,270,14,N
-hepatitis,Multivariate,Classification (Binary),Class,None,154,32,Y
-income,Multivariate,Classification (Binary),income >50K,None,32561,14,Y
-juice,Multivariate,Classification (Binary),Purchase,None,1070,15,N
-nba,Multivariate,Classification (Binary),TARGET_5Yrs,None,1340,21,N
-wine,Multivariate,Classification (Binary),type,None,6498,13,N
-telescope,Multivariate,Classification (Binary),Class,None,19020,11,N
-us_presidential_election_results,Multivariate,Classification (Binary),party_winner,None,497,7,N
-glass,Multivariate,Classification (Multiclass),Type,None,214,10,N
-iris,Multivariate,Classification (Multiclass),species,None,150,5,N
-poker,Multivariate,Classification (Multiclass),CLASS,None,100000,11,N
-questions,Multivariate,Classification (Multiclass),Next_Question,None,499,4,N
-satellite,Multivariate,Classification (Multiclass),Class,None,6435,37,N
-asia_gdp,Multivariate,Clustering,None,None,40,11,N
-elections,Multivariate,Clustering,None,None,3195,54,Y
-facebook,Multivariate,Clustering,None,None,7050,12,N
-ipl,Multivariate,Clustering,None,None,153,25,N
-jewellery,Multivariate,Clustering,None,None,505,4,N
-mice,Multivariate,Clustering,None,None,1080,82,Y
-migration,Multivariate,Clustering,None,None,233,12,N
-perfume,Multivariate,Clustering,None,None,20,29,N
-pokemon,Multivariate,Clustering,None,None,800,13,Y
-population,Multivariate,Clustering,None,None,255,56,Y
-public_health,Multivariate,Clustering,None,None,224,21,N
-seeds,Multivariate,Clustering,None,None,210,7,N
-wholesale,Multivariate,Clustering,None,None,440,8,N
-tweets,Text,NLP,tweet,None,8594,2,N
-amazon,Text,NLP / Classification,reviewText,None,20000,2,N
-kiva,Text,NLP / Classification,en,None,6818,7,N
-spx,Text,NLP / Regression,text,None,874,4,N
-wikipedia,Text,NLP / Classification,Text,None,500,3,N
-automobile,Multivariate,Regression,price,None,202,26,Y
-bike,Multivariate,Regression,cnt,None,17379,15,N
-boston,Multivariate,Regression,medv,None,506,14,N
-concrete,Multivariate,Regression,strength,None,1030,9,N
-diamond,Multivariate,Regression,Price,None,6000,8,N
-energy,Multivariate,Regression,Heating Load,Cooling Load,768,10,N
-forest,Multivariate,Regression,area,None,517,13,N
-gold,Multivariate,Regression,Gold_T+22,None,2558,121,N
-house,Multivariate,Regression,SalePrice,None,1461,81,Y
-insurance,Multivariate,Regression,charges,None,1338,7,N
-parkinsons,Multivariate,Regression,PPE,None,5875,22,N
-traffic,Multivariate,Regression,traffic_volume,None,48204,8,N
-CTG, Multivariate, Classification (Multiclass), NSP,None,2129,40,Y
+Dataset,Data Types,Default Task,Target Variable 1,Target Variable 2,# Instances,# Attributes,Missing Values
+anomaly,Multivariate,Anomaly Detection,None,None,1000,10,N
+france,Multivariate,Association Rule Mining,InvoiceNo,Description,8557,8,N
+germany,Multivariate,Association Rule Mining,InvoiceNo,Description,9495,8,N
+bank,Multivariate,Classification (Binary),deposit,None,45211,17,N
+blood,Multivariate,Classification (Binary),Class,None,748,5,N
+cancer,Multivariate,Classification (Binary),Class,None,683,10,N
+credit,Multivariate,Classification (Binary),default,None,24000,24,N
+diabetes,Multivariate,Classification (Binary),Class variable,None,768,9,N
+electrical_grid,Multivariate,Classification (Binary),stabf,None,10000,14,N
+employee,Multivariate,Classification (Binary),left,None,14999,10,N
+heart,Multivariate,Classification (Binary),DEATH,None,200,16,N
+heart_disease,Multivariate,Classification (Binary),Disease,None,270,14,N
+hepatitis,Multivariate,Classification (Binary),Class,None,154,32,Y
+income,Multivariate,Classification (Binary),income >50K,None,32561,14,Y
+juice,Multivariate,Classification (Binary),Purchase,None,1070,15,N
+nba,Multivariate,Classification (Binary),TARGET_5Yrs,None,1340,21,N
+wine,Multivariate,Classification (Binary),type,None,6498,13,N
+telescope,Multivariate,Classification (Binary),Class,None,19020,11,N
+us_presidential_election_results,Multivariate,Classification (Binary),party_winner,None,497,7,N
+glass,Multivariate,Classification (Multiclass),Type,None,214,10,N
+iris,Multivariate,Classification (Multiclass),species,None,150,5,N
+poker,Multivariate,Classification (Multiclass),CLASS,None,100000,11,N
+questions,Multivariate,Classification (Multiclass),Next_Question,None,499,4,N
+satellite,Multivariate,Classification (Multiclass),Class,None,6435,37,N
+asia_gdp,Multivariate,Clustering,None,None,40,11,N
+elections,Multivariate,Clustering,None,None,3195,54,Y
+facebook,Multivariate,Clustering,None,None,7050,12,N
+ipl,Multivariate,Clustering,None,None,153,25,N
+jewellery,Multivariate,Clustering,None,None,505,4,N
+mice,Multivariate,Clustering,None,None,1080,82,Y
+migration,Multivariate,Clustering,None,None,233,12,N
+perfume,Multivariate,Clustering,None,None,20,29,N
+pokemon,Multivariate,Clustering,None,None,800,13,Y
+population,Multivariate,Clustering,None,None,255,56,Y
+public_health,Multivariate,Clustering,None,None,224,21,N
+seeds,Multivariate,Clustering,None,None,210,7,N
+wholesale,Multivariate,Clustering,None,None,440,8,N
+tweets,Text,NLP,tweet,None,8594,2,N
+amazon,Text,NLP / Classification,reviewText,None,20000,2,N
+kiva,Text,NLP / Classification,en,None,6818,7,N
+spx,Text,NLP / Regression,text,None,874,4,N
+wikipedia,Text,NLP / Classification,Text,None,500,3,N
+automobile,Multivariate,Regression,price,None,202,26,Y
+bike,Multivariate,Regression,cnt,None,17379,15,N
+boston,Multivariate,Regression,medv,None,506,14,N
+concrete,Multivariate,Regression,strength,None,1030,9,N
+diamond,Multivariate,Regression,Price,None,6000,8,N
+energy,Multivariate,Regression,Heating Load,Cooling Load,768,10,N
+forest,Multivariate,Regression,area,None,517,13,N
+gold,Multivariate,Regression,Gold_T+22,None,2558,121,N
+house,Multivariate,Regression,SalePrice,None,1461,81,Y
+insurance,Multivariate,Regression,charges,None,1338,7,N
+parkinsons,Multivariate,Regression,PPE,None,5875,22,N
+traffic,Multivariate,Regression,traffic_volume,None,48204,8,N
+CTG, Multivariate, Classification (Multiclass),NSP,None,2129,40,Y

pycaret/tests/test_anomaly.py

@@ -12,7 +12,7 @@ def test():
     assert isinstance(data, pd.core.frame.DataFrame)
 
     # init setup
-    ano1 = pycaret.anomaly.setup(data, normalize=True, silent=True, html=False, session_id=123)
+    ano1 = pycaret.anomaly.setup(data, normalize=True, log_experiment=True, silent=True, html=False, session_id=123)
     assert isinstance(ano1, tuple)
 
     # create model

pycaret/tests/test_classification.py

@@ -13,8 +13,27 @@ def test():
     assert isinstance(data, pd.core.frame.DataFrame)
 
     # init setup
-    clf1 = pycaret.classification.setup(data, target='Purchase', silent=True, html=False, session_id=123)
+    clf1 = pycaret.classification.setup(data, target='Purchase', log_experiment=True, silent=True, html=False, session_id=123)
     assert isinstance(clf1, tuple)
+    assert isinstance(clf1[0], pd.core.frame.DataFrame)
+    assert isinstance(clf1[1], pd.core.series.Series)
+    assert isinstance(clf1[2], pd.core.frame.DataFrame)
+    assert isinstance(clf1[3], pd.core.frame.DataFrame)
+    assert isinstance(clf1[4], pd.core.series.Series)
+    assert isinstance(clf1[5], pd.core.series.Series)
+    assert isinstance(clf1[6], int)
+    assert isinstance(clf1[8], list)
+    assert isinstance(clf1[9], bool)
+    assert isinstance(clf1[10], int)
+    assert isinstance(clf1[11], bool)
+    assert isinstance(clf1[12], list)
+    assert isinstance(clf1[13], list)
+    assert isinstance(clf1[14], list)
+    assert isinstance(clf1[15], str)
+    assert isinstance(clf1[16], bool)
+    assert isinstance(clf1[17], bool)
+    assert isinstance(clf1[18], str)
+    assert isinstance(clf1[19], bool)
 
     # compare models
     top3 = pycaret.classification.compare_models(n_select = 3, exclude=['catboost'])

pycaret/tests/test_clustering.py

@@ -12,7 +12,7 @@ def test():
     assert isinstance(data, pd.core.frame.DataFrame)
 
     # init setup
-    clu1 = pycaret.clustering.setup(data, normalize = True, silent=True, html=False, session_id=123)
+    clu1 = pycaret.clustering.setup(data, normalize = True, log_experiment=True, silent=True, html=False, session_id=123)
     assert isinstance(clu1, tuple)
 
     # create model

pycaret/tests/test_datasets.py

@@ -10,7 +10,7 @@ def test():
     data = pycaret.datasets.get_data('index')
     assert isinstance(data, pd.core.frame.DataFrame)
     row, col = data.shape
-    assert row <= 54
+    assert row > 1
     assert col == 7
 
     # loading dataset

pycaret/tests/test_nlp.py

@@ -13,7 +13,7 @@ def test():
     assert isinstance(data, pd.core.frame.DataFrame)
 
     # init setup
-    nlp1 = pycaret.nlp.setup(data = data, target = 'en', html=False, session_id = 123)
+    nlp1 = pycaret.nlp.setup(data = data, target = 'en', log_experiment=True, html=False, session_id = 123)
     assert isinstance(nlp1, tuple)
 
     # create model

pycaret/tests/test_regression.py

@@ -12,7 +12,7 @@ def test():
     assert isinstance(data, pd.core.frame.DataFrame)
 
     # init setup
-    reg1 = pycaret.regression.setup(data, target='medv',silent=True, html=False, session_id=123)
+    reg1 = pycaret.regression.setup(data, target='medv',silent=True, log_experiment=True, html=False, session_id=123)
     assert isinstance(reg1, tuple)
 
     # compare models