def run_single_validation(self, grid_size, validation_date, time_unit):
data = ProcessData(self.dataset_info['name'], self.dataset_info['path'])
df = data.get_formated_df()
self.dataset_info['dict'] = data.dataset_dict #update dataset dictionary on experiment instance
df_filtered = ProcessData.filter_by_field(df, self.custom_filter['field'], self.custom_filter['value'])
validation = ValidateModel(df_filtered, self.dataset_info['dict'], time_unit, None)
prediction_results = validation.inner_loop_validation(self.model, grid_size, self.train_dates, datetime.strptime(validation_date,'%Y-%m-%d'), self.metrics)
return prediction_results
def test_hit_rate_2(self):
""" Test hit_rate=0 if no events falls on hotspots """
df = pd.read_csv(
"/Users/anamaria/Desktop/dev/security_project/datasets/deduplicate_siedco_09062020.csv"
)
data = ProcessData(
"SIEDCO",
"/Users/anamaria/Desktop/dev/security_project/datasets/deduplicate_siedco_09062020.csv"
)
df_input = data.add_timestamp(df)
date = '2018-01-01'
dataset_dict = data.dataset_dict
df_input = ProcessData.filter_by_date(df_input, dataset_dict, date,
date)
df_1 = ProcessData.filter_by_field(df_input, 'LOCALIDAD', 'SUBA')
df_2 = ProcessData.filter_by_field(df_input, 'LOCALIDAD', 'BOSA')
timed_pts, region = ProcessData.get_time_space_points(
df_1, data.dataset_dict)
counting_kernel = open_cp.naive.CountingGridKernel(grid_width=150,
region=region)
counting_kernel.data = timed_pts
grid_prediction = counting_kernel.predict()
coverages = [2, 4, 6, 8, 10]
eval_pts, _ = ProcessData.get_time_space_points(
df_2, data.dataset_dict)
hit_rates_default = prediction_metrics.measure_hit_rates(
grid_prediction, eval_pts, coverages, 'default')
hit_rates_ground_truth = prediction_metrics.measure_hit_rates(
grid_prediction, eval_pts, coverages, 'ground_truth_coverage')
self.assertEqual(hit_rates_default, {
2: 0.0,
4: 0.0,
6: 0.0,
8: 0.0,
10: 0.0
})
self.assertEqual(hit_rates_ground_truth, {0.6632653061224489: 0.0})
def train(self, df_train_subset, dataset_dict, grid_size, **kwargs):
df_train_subset['weekday'] = df_train_subset['TIME_STAMP'].dt.day_name(
)
df_train_subset = ProcessData.filter_by_field(df_train_subset,
'weekday',
kwargs['week_day'])
train_pts, train_region = ProcessData.get_time_space_points(
df_train_subset, dataset_dict)
if (isinstance(kwargs['region'], open_cp.data.RectangularRegion)):
train_region = kwargs['region']
trainer = seppexp.SEPPTrainer(region=train_region, grid_size=grid_size)
trainer.data = train_pts
trained_model = trainer.train(iterations=50, use_corrected=True)
trained_model.data = train_pts
return trained_model
def test_filter_by_field_case4(self):
#case 4: error, value doesn't exist
df = pd.read_csv(self.my_data.dataset_path)
self.assertRaises(
ValueError,
lambda: ProcessData.filter_by_field(df, 'LOCALIDAD', 'NORMANDIA'))
def test_filter_by_field_case3(self):
#case 3: error, field doesn't exist
df = pd.read_csv(self.my_data.dataset_path)
self.assertRaises(
ValueError,
lambda: ProcessData.filter_by_field(df, 'nombre', 'Pedro'))
def test_filter_by_field_case2(self):
#case 2: filter successful, without field value
df = pd.read_csv(self.my_data.dataset_path)
df_filtered = ProcessData.filter_by_field(df, '', '')
assertion_proxy = df_filtered.equals(df)
self.assertEqual(assertion_proxy, True)
def test_filter_by_field_case1(self):
#case 1: filter successful
df = pd.read_csv(self.my_data.dataset_path)
df_filtered = ProcessData.filter_by_field(df, 'LOCALIDAD', 'BOSA')
self.assertEqual(df_filtered.LOCALIDAD.unique()[0], 'BOSA')