def test_fit_and_transform(self):
augmenter = FeatureAugmenter(column_value="val", column_id="id", column_sort="sort",
column_kind="kind",
kind_to_fc_parameters=self.kind_to_fc_parameters)
# Fit should do nothing
returned_df = augmenter.fit()
six.assertCountEqual(self, returned_df.__dict__, augmenter.__dict__)
self.assertRaises(RuntimeError, augmenter.transform, None)
augmenter.set_timeseries_container(self.test_df)
# Add features to all time series
X_with_index = pd.DataFrame([{"feature_1": 1}]*2, index=[10, 500])
X_transformed = augmenter.transform(X_with_index)
# Require same shape
for i in X_transformed.index:
self.assertIn(i, X_with_index.index)
for i in X_with_index.index:
self.assertIn(i, X_transformed.index)
self.assertEqual(X_transformed.shape, (2, 3))
# Preserve old features
six.assertCountEqual(self, list(X_transformed.columns), ["feature_1", "a__length", "b__length"])
# Features are not allowed to be NaN
for index, row in X_transformed.iterrows():
print((index, row))
self.assertFalse(np.isnan(row["a__length"]))
self.assertFalse(np.isnan(row["b__length"]))
def test_add_features_to_only_a_part(self):
augmenter = FeatureAugmenter(column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind",
settings=self.settings)
augmenter.set_timeseries_container(self.test_df)
X_with_not_all_ids = pd.DataFrame([{"feature_1": 1}], index=[1])
X_transformed = augmenter.transform(X_with_not_all_ids)
for i in X_transformed.index:
self.assertIn(i, X_with_not_all_ids.index)
for i in X_with_not_all_ids.index:
self.assertIn(i, X_transformed.index)
self.assertEqual(X_transformed.shape, (1, 3))
self.assertEqual(X_transformed.index, [1])
# Features are not allowed to be NaN
for index, row in X_transformed.iterrows():
print(index, row)
self.assertFalse(np.isnan(row["a__length"]))
self.assertFalse(np.isnan(row["b__length"]))
def test_add_features_to_only_a_part(self):
augmenter = FeatureAugmenter(column_value="val", column_id="id", column_sort="sort",
column_kind="kind",
kind_to_fc_parameters=self.kind_to_fc_parameters,
n_jobs=0,
disable_progressbar = True)
augmenter.set_timeseries_container(self.test_df)
X_with_not_all_ids = pd.DataFrame([{"feature_1": 1}], index=[10])
X_transformed = augmenter.transform(X_with_not_all_ids)
for i in X_transformed.index:
self.assertIn(i, X_with_not_all_ids.index)
for i in X_with_not_all_ids.index:
self.assertIn(i, X_transformed.index)
self.assertEqual(X_transformed.shape, (1, 3))
self.assertEqual(X_transformed.index, [10])
# Features are not allowed to be NaN
for index, row in X_transformed.iterrows():
print((index, row))
self.assertFalse(np.isnan(row["a__length"]))
self.assertFalse(np.isnan(row["b__length"]))
def test_no_ids_present(self):
augmenter = FeatureAugmenter(
column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind",
kind_to_fc_parameters=self.kind_to_fc_parameters,
n_jobs=0,
disable_progressbar=True)
augmenter.set_timeseries_container(self.test_df)
X_with_not_all_ids = pd.DataFrame([{"feature_1": 1}], index=[-999])
self.assertRaisesRegex(AttributeError,
r"The ids of the time series container",
augmenter.transform, X_with_not_all_ids)
def run(filename='data/clean_data.csv', city_regions_file='data/CityRegions.csv', load_from_file=True, grid_search=False, baseline=False):
if city_regions_file == None:
temp = [['Abiline', 'Texas','South'],['West Jordon', 'Utah', 'West' ], ['Yonkers','New York', 'Northeast']]
city_regions = pd.DataFrame(temp, columns=['City', 'State','Region'])
else:
city_regions = pd.read_csv(city_regions_file, header=0).reset_index(drop=True)
FEATURE_EXTRACTION='data/data_with_features.csv'
if not os.path.isfile(FEATURE_EXTRACTION):
df = pd.read_csv(filename, header=0)
df.dropna(inplace=True)
X_labels = ['City', 'State', 'dt', 'AverageTemperature', 'CityIndex']
df = df[X_labels]
df = df.dropna()
#city_state = df[['City', 'State']]
# Sadness because multiple cities with same name.......
#df['CityIndex'] = city_state.apply(number_cities, axis=1)
#df.to_csv('data/clean_data.csv', index=False)
orig_cities = city_regions[['City','State']]
print "Total cities ", len(orig_cities)
y_regions = city_regions['Region']
y_regions = y_regions.apply(number_regions)
feature_extraction_settings = FeatureExtractionSettings()
feature_extraction_settings.IMPUTE = impute
feat_extractor = FeatureAugmenter(feature_extraction_settings,
column_id='CityIndex', column_sort='dt', column_value='AverageTemperature')
empty_df = pd.DataFrame(index=y_regions.index)
feat_extractor.set_timeseries_container(df)
output = feat_extractor.fit_transform(empty_df,y_regions)
output['City'] = city_regions['City']
output['State'] = city_regions['State']
output['Region'] = city_regions['Region']
output.to_csv(FEATURE_EXTRACTION, index=False)
else:
output = pd.read_csv(FEATURE_EXTRACTION)
output = output.drop(['City', 'State', 'Region'], axis=1)
if baseline:
output = output['AverageTemperature__mean'].to_frame()
train, test, validation = split_data(output, city_regions)
"""
aug = FeatureAugmenter(feature_extraction_settings, column_id='CityIndex',
column_sort='dt', column_value='AverageTemperature',
timeseries_container=train['df'])
output = aug.fit_transform(train['X'], train['y'])
output['City_Name'] = train['city_names']
output.to_csv('data/features_from_tsfresh.csv', index=False)
"""
if load_from_file:
clf = joblib.load('./model.joblib.pkl')
else:
clf = DecisionTreeClassifier(criterion='entropy', max_features=None,
min_samples_split=0.1, max_depth=50, class_weight=None)
# feat_extractor = RelevantFeatureAugmenter(column_id='CityIndex', column_sort='dt', column_value='AverageTemperature')
# for the fit on the train test set, we set the fresh__timeseries_container to `df_train`
if grid_search and not baseline:
grid = {'max_features': [2, 10, 20, 30, 50, 100, 200, None],
'max_depth': [1, 25, 50, 100],
'class_weight': [None, 'balanced'],
'min_samples_split': [0.1, 0.25, 0.75, 1.0]}
scorer = metrics.make_scorer(partial(metrics.accuracy_score))
clf = GridSearchCV(clf, grid, scoring=scorer, n_jobs=multiprocessing.cpu_count())
clf.fit(train['X'], train['y'])
# pipeline.set_params(augmenter__timeseries_container=train['df'])
# pipeline.fit(train['X'], train['y'])
y_pred = pd.Series(clf.predict(train['X']))
y_true = pd.Series(np.array(train['y']))
result = train['city_names']
result.reset_index(drop=True, inplace=True)
result['Orig'] = y_true
result['Pred'] = y_pred
wrongs = y_true == y_pred
result['Correct'] = wrongs
result.to_csv('data/results_train.csv', index=False)
if grid_search and not baseline:
print "Best Parameters found from grid search: "
print clf.best_params_
print "train accuracy ", accuracy_score(y_true, y_pred)
cm_train = confusion_matrix(y_true, y_pred)
print "Confusion matrix for training\n", cm_train
# for the predict on the test test set, we set the fresh__timeseries_container to `df_test`
joblib.dump(clf, './model.joblib.pkl')
#### ENDIF
y_pred = pd.Series(clf.predict(test['X']))
y_true = pd.Series(np.array(test['y']))
result = test['city_names']
result.reset_index(drop=True, inplace=True)
result['Orig'] = y_true
result['Pred'] = y_pred
wrongs = y_true == y_pred
result['Correct'] = wrongs
result.to_csv('data/results_test.csv', index=False)
print "test accuracy ", accuracy_score(y_true, y_pred)
cm_test = confusion_matrix(y_true, y_pred)
print "Confusion matrix for testing\n", cm_test
class_names = ['Northeast', 'Midwest', 'West', 'South']
if not load_from_file:
plot_confusion_matrix(cm_train, class_names)
plt.tight_layout()
plt.savefig('train_cm.png')
plt.hold(False)
plot_confusion_matrix(cm_test, class_names)
plt.tight_layout()
plt.savefig('test_cm.png')
if not load_from_file and not grid_search:
features = output.columns.values
importances = clf.feature_importances_
with open("tree_viz.dot", "w") as f:
f = tree.export_graphviz(clf, out_file=f)
top_n = 20
ndx = np.argsort(importances)[::-1]
sorted_features = features[ndx][:20]
sorted_importances = importances[ndx][:20]
print '%80s & %s' %('Feature', 'Importance')
for f, i in zip(sorted_features, sorted_importances):
# print '%80s & %.2f \\\\' % (f[20:], i)
print '%s & %.2f \\\\' % (f[20:], i)
y_pred = clf.predict(validation['X'])
y_true = np.array(validation['y'])
y_pred = pd.Series(clf.predict(validation['X']))
y_true = pd.Series(np.array(validation['y']))
result = validation['city_names']
result.reset_index(drop=True, inplace=True)
result['Orig'] = y_true
result['Pred'] = y_pred
wrongs = y_true == y_pred
result['Correct'] = wrongs
result.to_csv('data/results_val.csv', index=False)
print "validation accuracy ", accuracy_score(y_true, y_pred)
cm_val = confusion_matrix(y_true, y_pred)
print "Confusion matrix for validation\n", cm_val
print "done"
class_names = ['Northeast', 'Midwest', 'West', 'South']
plt.hold(False)
plot_confusion_matrix(cm_val, class_names)
plt.tight_layout()
plt.savefig('val_cm.png')