Analytic types (#573)

analytics/analytics/analytic_types/__init__.py

@@ -0,0 +1,14 @@
+"""
+It is the place where we put all classes and types
+which is common for all of the code.
+
+For example, if you write someting which is used
+in analytic_unit_manager, it should be here.
+
+If you create something spicific which is used only in one place, 
+like PatternDetectionCache, then it should not be here.
+"""
+
+from analytic_types.data_bucket import DataBucket
+
+AnalyticUnitId = str

analytics/analytics/analytic_types/data_bucket.py

@@ -1,5 +1,6 @@
 import pandas as pd
 
+
 class DataBucket(object):
 
     data: pd.DataFrame

analytics/analytics/analytic_unit_manager.py

@@ -4,14 +4,13 @@ import traceback
 from concurrent.futures import Executor, ThreadPoolExecutor
 
 from analytic_unit_worker import AnalyticUnitWorker
+from analytic_types import AnalyticUnitId
 import detectors
 from models import ModelCache
 
 
 logger = log.getLogger('AnalyticUnitManager')
 
-AnalyticUnitId = str
-
 
 def get_detector_by_type(
     detector_type: str, analytic_unit_type: str, analytic_unit_id: AnalyticUnitId

analytics/analytics/buckets/__init__.py

@@ -1 +0,0 @@
-from buckets.data_bucket import DataBucket

analytics/analytics/detectors/pattern_detector.py

@@ -8,9 +8,10 @@ import pandas as pd
 from typing import Optional, Generator
 
 from detectors import Detector
-from buckets import DataBucket
+from analytic_types import DataBucket
 from models import ModelCache
 from utils import convert_pd_timestamp_to_ms
+from analytic_types import AnalyticUnitId
 
 
 logger = logging.getLogger('PATTERN_DETECTOR')
@@ -31,7 +32,7 @@ def resolve_model_by_pattern(pattern: str) -> models.Model:
         return models.CustomModel()
     raise ValueError('Unknown pattern "%s"' % pattern)
 
-AnalyticUnitId = str
+
 class PatternDetector(Detector):
 
     MIN_BUCKET_SIZE = 150

analytics/analytics/models/general_model.py

@@ -11,6 +11,8 @@ import math
 from scipy.stats import gaussian_kde
 from scipy.stats import norm
 import logging
+from analytic_types import AnalyticUnitId
+
 
 PEARSON_FACTOR = 0.7
 
@@ -39,8 +41,8 @@ class GeneralModel(Model):
         center_ind = start + math.ceil((end - start) / 2)
         return center_ind
 
-    def do_fit(self, dataframe: pd.DataFrame, labeled_segments: list, deleted_segments: list, learning_info: dict, AnalyticUnitId: str) -> None:
+    def do_fit(self, dataframe: pd.DataFrame, labeled_segments: list, deleted_segments: list, learning_info: dict, id: AnalyticUnitId) -> None:
-        logging.debug('Start method do_fit for analytic unit: {}'.format(AnalyticUnitId))
+        logging.debug('Start method do_fit for analytic unit: {}'.format(id))
         data = utils.cut_dataframe(dataframe)
         data = data['value']
         last_pattern_center = self.state.get('pattern_center', [])
@@ -61,10 +63,10 @@ class GeneralModel(Model):
 
         self.state['convolve_min'], self.state['convolve_max'] = utils.get_min_max(convolve_list, self.state['WINDOW_SIZE'] / 3)
         self.state['conv_del_min'], self.state['conv_del_max'] = utils.get_min_max(del_conv_list, self.state['WINDOW_SIZE'])
-        logging.debug('Method do_fit completed correctly for analytic unit: {}'.format(AnalyticUnitId))
+        logging.debug('Method do_fit completed correctly for analytic unit: {}'.format(id))
 
-    def do_detect(self, dataframe: pd.DataFrame, AnalyticUnitId: str) -> List[int]:
+    def do_detect(self, dataframe: pd.DataFrame, id: AnalyticUnitId) -> List[int]:
-        logging.debug('Start method do_detect for analytic unit: {}'.format(AnalyticUnitId))
+        logging.debug('Start method do_detect for analytic unit: {}'.format(id))
         data = utils.cut_dataframe(dataframe)
         data = data['value']
         pat_data = self.state.get('pattern_model', [])
@@ -76,7 +78,7 @@ class GeneralModel(Model):
         all_corr_peaks = utils.find_peaks(all_corr, window_size * 2)
         filtered = self.__filter_detection(all_corr_peaks, data)
         filtered = list(filtered)
-        logging.debug('Method do_detect completed correctly for analytic unit: {}'.format(AnalyticUnitId))
+        logging.debug('Method do_detect completed correctly for analytic unit: {}'.format(id))
         return [(item, item + window_size * 2) for item in filtered]
 
     def __filter_detection(self, segments:  Generator[int, None, None], data: pd.Series) -> Generator[int, None, None]:

analytics/analytics/models/model.py

@@ -6,6 +6,7 @@ from typing import Optional
 import pandas as pd
 import math
 import logging
+from analytic_types import AnalyticUnitId
 
 ModelCache = dict
 
@@ -62,9 +63,8 @@ class Model(ABC):
     @abstractmethod
     def get_model_type(self) -> (str, bool):
         pass
-        
+
-    # TODO: id: str -> id: AnalyticUnitId in all models
+    def fit(self, dataframe: pd.DataFrame, segments: list, id: AnalyticUnitId, cache: Optional[ModelCache]) -> ModelCache:
-    def fit(self, dataframe: pd.DataFrame, segments: list, id: str, cache: Optional[ModelCache]) -> ModelCache:
         logging.debug('Start method fit for analytic unit {}'.format(id))
         data = dataframe['value']
         if cache != None and len(cache) > 0: