From 70a9dbe63faebfce87e2d19a738a40d104eed5a9 Mon Sep 17 00:00:00 2001
From: Eric Schles <ericschles@Erics-MacBook-Pro.local>
Date: Thu, 12 Aug 2021 15:57:36 -0400
Subject: [PATCH 1/2] adding a new test for reasons

---
 tests/test_regression_tests.py | 46 ++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/tests/test_regression_tests.py b/tests/test_regression_tests.py
index 19a8132..f0faffb 100644
--- a/tests/test_regression_tests.py
+++ b/tests/test_regression_tests.py
@@ -28,6 +28,31 @@ def generate_regression_data_and_models():
     reg2.fit(X, df[target_name])
     return df, column_names, target_name, reg1, reg2
 
+def generate_regression_data_and_models_with_large_data():
+    df = pd.DataFrame()
+    for _ in range(1000):
+        a = np.random.normal(0, 1)
+        b = np.random.normal(0, 3)
+        c = np.random.normal(12, 4)
+        d = np.random.normal(1500, 27000)
+        target = (a + b + c) * d
+        df = df.append({
+            "A": a,
+            "B": b,
+            "C": c,
+            "D": d,
+            "target": target
+        }, ignore_index=True)
+
+    reg1 = tree.DecisionTreeRegressor()
+    reg2 = ensemble.RandomForestRegressor()
+    column_names = ["A", "B", "C", "D"]
+    target_name = "target"
+    X = df[column_names]
+    reg1.fit(X, df[target_name])
+    reg2.fit(X, df[target_name])
+    return df, column_names, target_name, reg1, reg2
+
 def test_regression_basic():
     df, column_names, target_name, reg, _ = generate_regression_data_and_models()
     test_suite = regression_tests.RegressionTests(reg,
@@ -49,6 +74,27 @@ def test_regression_basic():
     except:
         assert False
 
+def test_regression_basic_with_large_data():
+    df, column_names, target_name, reg, _ = generate_regression_data_and_models_with_large_data()
+    test_suite = regression_tests.RegressionTests(reg,
+                                                  df,
+                                                  target_name,
+                                                  column_names)
+    try:
+        mse_upper_boundary = 10000
+        mae_upper_boundary = 10000
+        tse_upper_boundary = 10000
+        tae_upper_boundary = 10000
+        test_suite.upper_bound_regression_testing(
+            mse_upper_boundary,
+            mae_upper_boundary,
+            tse_upper_boundary,
+            tae_upper_boundary
+        )
+        assert True
+    except:
+        assert False
+
 def test_cross_val_mse_anomaly_detection():
     df, column_names, target_name, reg, _ = generate_regression_data_and_models()
     test_suite = regression_tests.RegressionTests(reg,

From 611ad619e8598f124583d8bc0e53c9bacdd66e68 Mon Sep 17 00:00:00 2001
From: Eric Schles <ericschles@Erics-MacBook-Pro.local>
Date: Thu, 4 Nov 2021 15:50:39 -0400
Subject: [PATCH 2/2] adding e

---
 tests/test_regression_tests.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tests/test_regression_tests.py b/tests/test_regression_tests.py
index f0faffb..cd8e760 100644
--- a/tests/test_regression_tests.py
+++ b/tests/test_regression_tests.py
@@ -35,18 +35,20 @@ def generate_regression_data_and_models_with_large_data():
         b = np.random.normal(0, 3)
         c = np.random.normal(12, 4)
         d = np.random.normal(1500, 27000)
-        target = (a + b + c) * d
+        e = np.random.normal(1, 2)
+        target = ((a + b + c) * d)/e
         df = df.append({
             "A": a,
             "B": b,
             "C": c,
             "D": d,
+            "E": e,
             "target": target
         }, ignore_index=True)
 
     reg1 = tree.DecisionTreeRegressor()
     reg2 = ensemble.RandomForestRegressor()
-    column_names = ["A", "B", "C", "D"]
+    column_names = ["A", "B", "C", "D", "E"]
     target_name = "target"
     X = df[column_names]
     reg1.fit(X, df[target_name])