update unit tests

.ipynb_checkpoints/Untitled-checkpoint.ipynb

-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 2
-}

.log

@@ -54,3 +54,14 @@
 2020-05-05 14:06:24,431 [413656] INFO     numexpr.utils:129: [JupyterRequire] Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
 2020-05-05 14:06:24,432 [413656] INFO     numexpr.utils:141: [JupyterRequire] NumExpr defaulting to 8 threads.
 2020-05-05 14:06:24,697 [413656] DEBUG    matplotlib.pyplot:225: [JupyterRequire] Loaded backend module://ipykernel.pylab.backend_inline version unknown.
+2020-05-05 15:23:24,077 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\ensemble\_bagging.py
+2020-05-05 15:23:24,500 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\jedi\third_party\typeshed\stdlib\2and3\builtins.pyi
+2020-05-05 15:23:24,543 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\ensemble\_base.py
+2020-05-05 15:23:24,574 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\base.py
+2020-05-05 15:23:24,638 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\numpy\__init__.py
+2020-05-05 15:23:24,682 [413656] DEBUG    parso.cache:126: [JupyterRequire] pickle loaded: C:\Users\mali085\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\tree\_classes.py
+2020-05-05 15:32:17,197 [413656] DEBUG    parso.python.diff:213: [JupyterRequire] diff parser start
+2020-05-05 15:32:17,198 [413656] DEBUG    parso.python.diff:224: [JupyterRequire] line_lengths old: 1; new: 1
+2020-05-05 15:32:17,199 [413656] DEBUG    parso.python.diff:228: [JupyterRequire] -> code[replace] old[1:1] new[1:1]
+2020-05-05 15:32:17,201 [413656] DEBUG    parso.python.diff:341: [JupyterRequire] parse_part from 1 to 1 (to 0 in part parser)
+2020-05-05 15:32:17,202 [413656] DEBUG    parso.python.diff:264: [JupyterRequire] diff parser end

.travis.yml

 language: python
 python:
+  - 3.4
+  - 3.5
+  - 3.6
   - 3.7
   - 3.8
 before_install:

pycaret/tests/test_compare_models.py

@@ -8,6 +8,7 @@ import pycaret.datasets
 
 def test_compare_models():
     data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
     reg1 = pycaret.regression.setup(data, target='medv',silent=True, html=False, session_id=123)
     models = pycaret.regression.compare_models(n_select=3)
     top_3 = len(models)

pycaret/tests/test_create_model.py

@@ -8,10 +8,13 @@ import pycaret.datasets
 
 available_regressors = ['lr', 'lasso', 'ridge', 'en', 'lar', 'llar', 'omp', 'br', 'ard', 'par', 
                             'ransac', 'tr', 'huber', 'kr', 'svm', 'knn', 'dt', 'rf', 'et', 'ada', 'gbr', 
-                            'mlp', 'xgboost', 'lightgbm', 'catboost']
+                            'mlp', 'xgboost', 'lightgbm'] #catboost excluded from test
+
+#excluded catboost to speedup training
 
 def test_create_model():
     data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
     reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
     trained_models = []
     for i in available_regressors:

pycaret/tests/test_ensemble_model.py

+import os, sys
+sys.path.insert(0, os.path.abspath(".."))
+
+#ensemble_model_test
+import pytest
+import pycaret.regression
+import pycaret.datasets
+
+#Bagging
+def test_model_bagging():
+    data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
+    reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
+    model = pycaret.regression.ensemble_model(pycaret.regression.create_model('dt', verbose = False), verbose=False, method = 'Bagging')
+    assert hasattr(model, 'predict')
+
+#Boosting
+def test_model_boosting():
+    data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
+    reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
+    model = pycaret.regression.ensemble_model(pycaret.regression.create_model('et', verbose = False), verbose=False, method = 'Boosting')
+    assert hasattr(model, 'predict')
\ No newline at end of file

pycaret/tests/test_tune_model.py

@@ -6,15 +6,25 @@ import pytest
 import pycaret.regression
 import pycaret.datasets
 
-available_regressors = ['lr', 'lasso', 'ridge', 'en', 'lar', 'llar', 'omp', 'br', 'ard', 'par', 
-                            'ransac', 'tr', 'huber', 'kr', 'svm', 'knn', 'dt', 'rf', 'et', 'ada', 'gbr', 
-                            'mlp', 'xgboost', 'lightgbm', 'catboost']
+def test_model_tuning_r2():
+    data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
+    reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
+    model = pycaret.regression.tune_model(pycaret.regression.create_model('rf', verbose = False), verbose=False, optimize = 'r2')
+    assert hasattr(model, 'predict')
 
-def test_tune_model():
+def test_model_tuning_mae():
     data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
     reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
-    tuned_models = []
-    for i in available_regressors:
-        c = pycaret.regression.tune_model(estimator = pycaret.regression.create_model(i, verbose=False), verbose = False)
-        tuned_models.append(c)
-    assert len(tuned_models) == len(available_regressors)
\ No newline at end of file
+    model = pycaret.regression.tune_model(pycaret.regression.create_model('ada', verbose = False), verbose=False, optimize = 'mae')
+    assert hasattr(model, 'predict')
+
+def test_model_tuning_mse():
+    data = pycaret.datasets.get_data('boston')
+    data = data.head(50)
+    reg1 = pycaret.regression.setup(data, target='medv',silent=True, verbose=False, html=False, session_id=123)
+    model = pycaret.regression.tune_model(pycaret.regression.create_model('lr', verbose = False), verbose=False, optimize = 'mse')
+    assert hasattr(model, 'predict')
+
+