def test_feature_mismatching(self):
tpot = TPOTAdaptor(**self.common_tpot_kwargs)
target_key = "K_VRH"
df1 = self.train_df
df2 = self.test_df.rename(columns={'mean X': "some other feature"})
tpot.fit(df1, target_key)
with self.assertRaises(MatbenchError):
tpot.predict(df2, target_key)
def test_regression(self):
target_key = "K_VRH"
tpot = TPOTAdaptor(**self.common_tpot_kwargs)
tpot.fit(self.train_df, target_key)
test_w_predictions = tpot.predict(self.test_df, target_key)
y_true = test_w_predictions[target_key]
y_test = test_w_predictions[target_key + " predicted"]
self.assertTrue(r2_score(y_true, y_test) > 0.75)
def test_classification(self):
tpot = TPOTAdaptor(**self.common_tpot_kwargs)
max_kvrh = 50
classifier_key = "K_VRH > {}?".format(max_kvrh)
train_df = self.train_df.rename(columns={"K_VRH": classifier_key})
test_df = self.test_df.rename(columns={"K_VRH": classifier_key})
train_df[classifier_key] = train_df[classifier_key] > max_kvrh
test_df[classifier_key] = test_df[classifier_key] > max_kvrh
tpot.fit(train_df, classifier_key)
print(tpot.mode)
test_w_predictions = tpot.predict(test_df, classifier_key)
y_true = test_w_predictions[classifier_key]
y_test = test_w_predictions[classifier_key + " predicted"]
self.assertTrue(f1_score(y_true, y_test) > 0.75)
sleep(1)
# COMPARE TO MATBENCH
df = load_tehrani_superhard_mat(data="basic_descriptors")
df = df.drop(["formula", "material_id", "shear_modulus", "initial_structure"],
axis=1)
traindf = df.iloc[:floor(.8 * len(df))]
testdf = df.iloc[floor(.8 * len(df)):]
target = "bulk_modulus"
# Get top-level transformers
autofeater = AutoFeaturizer()
cleaner = DataCleaner()
reducer = FeatureReducer()
learner = TPOTAdaptor("regression", max_time_mins=5)
# Fit transformers on training data
traindf = autofeater.fit_transform(traindf, target)
traindf = cleaner.fit_transform(traindf, target)
traindf = reducer.fit_transform(traindf, target)
learner.fit(traindf, target)
# Apply the same transformations to the testing data
testdf = autofeater.transform(testdf, target)
testdf = cleaner.transform(testdf, target)
testdf = reducer.transform(testdf, target)
testdf = learner.predict(testdf, target) #predict validation data
print(testdf)