def inner_loop_validation(self, model_name, grid_size, train_subset_dates,current_validation_date):
model_object = globals()[model_name]()
df_train_subset = ProcessData.filter_by_date(self.df_train_validation,
self.dataset_dict,
train_subset_dates['initial'],
train_subset_dates['final'])
trained_model = model_object.train(df_train_subset, self.dataset_dict,
grid_size,
week_day= current_validation_date.strftime("%A"),
region= self.region)
print(len(trained_model.data.timestamps))
## TODO: save trained_model?
### validation
interval_duration = 6 ## TODO: set this var as a parameter
validation_dates = {'initial':current_validation_date,'final':current_validation_date}
df_validation = ProcessData.filter_by_date(self.df_train_validation,
self.dataset_dict,
validation_dates['initial'],
validation_dates['final'])
prediction_date = current_validation_date
flag_array = True
prediction_results = np.array([])
for interval_hour_start in range(0, 24, interval_duration):
initial_prediction_datetime = prediction_date+timedelta(hours=interval_hour_start)
final_prediction_datetime = initial_prediction_datetime+timedelta(hours=interval_duration)
if df_validation.empty: #if no points (e.g. crimes) are reported on data interval
eval_pts = []
else:
validation_pts, _ = ProcessData.get_time_space_points(df_validation,
self.dataset_dict)
eval_pts = ValidateModel.select_timed_points(prediction_date,
interval_hour_start,
interval_duration,
validation_pts)
prediction_by_hour = ValidateModel.predict_on_interval(initial_prediction_datetime,
interval_duration,
model_object,
trained_model)
average_prediction = ValidateModel.interval_average_prediction(prediction_by_hour)
element = np.array([initial_prediction_datetime,
final_prediction_datetime,
average_prediction,
eval_pts])
flag_array, prediction_results = ProcessData.fill_array(flag_array,
prediction_results,
element)
return prediction_results
def test_hit_rate_1(self):
""" Test hit_rate=1 if all real 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_filtered = ProcessData.filter_by_date(df_input, dataset_dict, date,
date)
timed_pts, region = ProcessData.get_time_space_points(
df_filtered, 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]
hit_rates_default = prediction_metrics.measure_hit_rates(
grid_prediction, timed_pts, coverages, 'default')
hit_rates_ground_truth = prediction_metrics.measure_hit_rates(
grid_prediction, timed_pts, coverages, 'ground_truth_coverage')
self.assertEqual(hit_rates_default, {
2: 1.0,
4: 1.0,
6: 1.0,
8: 1.0,
10: 1.0
})
self.assertEqual(hit_rates_ground_truth, {0.46187915216703573: 1.0})
def test_filter_by_date_case2(self):
#case 2: initial date out of available data, siedco
df = pd.read_csv(self.my_data.dataset_path)
df = self.my_data.add_timestamp(df)
initial_date = '2021-01-01'
final_date = '2021-01-02'
dataset_dict = self.my_data.dataset_dict
self.assertWarns(
UserWarning, lambda: ProcessData.filter_by_date(
df, dataset_dict, initial_date, final_date))
def test_filter_by_date_case1(self):
#case 1: date on interval, siedco
df = pd.read_csv(self.my_data.dataset_path)
df = self.my_data.add_timestamp(df)
initial_date = '2018-01-01'
final_date = '2018-01-01'
dataset_dict = self.my_data.dataset_dict
df_filtered = ProcessData.filter_by_date(df, dataset_dict,
initial_date, final_date)
df_expected = df.loc[df['FECHA_HECHO'] == "2018-01-01"]
self.assertEqual(len(df_filtered), len(df_expected))
def test_filter_by_date_case5(self):
#case 5: date on interval, rnmc
dataset = {'name': 'RNMC', 'path': ''}
self.my_data.dataset_name = 'RNMC'
self.my_data.dataset_dict = self.my_data.set_dictionary()
head_path = '/Users/anamaria/Desktop/dev/security_project/datasets/'
file = '06. verify_enrich_rnmc_12022020.csv'
df = pd.read_csv(head_path + file)
df = self.my_data.add_timestamp(df)
initial_date = '2018-01-01'
final_date = '2018-01-01'
dataset_dict = self.my_data.dataset_dict
df_filtered = ProcessData.filter_by_date(df, dataset_dict,
initial_date, final_date)
df_expected = df.loc[df['FECHA'] == "2018-01-01"]
self.assertEqual(len(df_filtered), len(df_expected))
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})