Added questionnaire data analyses pipeline

__init__.py

@@ -0,0 +1,3 @@
+from .questionnnairdataanalyses.features import (
+    QuestionnnairDataAnalyses
+)

config.yaml

@@ -0,0 +1,23 @@
+project:
+    project_name: Questionnnair data analyses
+    description: Questionnaire data analyses code from ART piplot analyses
+    version: 0.0
+
+input_data:
+    data_location: local
+    local_directory: /Users/heetsankesara/work/ART/data_cleaning/questionnaire_data/
+    data_format: csv
+
+configurations:
+    df_type: 'pandas'
+
+features:
+    - location: /Users/heetsankesara/work/RADAR/radar-pipeline/questionnnairdataanalyses
+      feature_groups:
+          - QuestionnnairDataAnalyses
+
+output_data:
+    output_location: local
+    local_directory: passive_output
+    data_format: csv
+    compress: false

questionnnairdataanalyses/features.py

@@ -0,0 +1,78 @@
+import pandas as pd
+from radarpipeline.datalib import RadarData
+from radarpipeline.features import Feature, FeatureGroup
+
+
+class QuestionnnairDataAnalyses(FeatureGroup):
+    def __init__(self):
+        name = "QuestionnnairDataAnalyses"
+        description = "contains Questionnnaire Data Features"
+        features = [QuestionnaireNotificationResponseLatency, QuestionnaireCompletionTime]
+        super().__init__(name, description, features)
+
+    def preprocess(self, data: RadarData) -> RadarData:
+        """
+        Preprocess the data for each feature in the group.
+        """
+        all_ques_list = {}
+        for key in self.required_input_data:
+            all_ques_list[key] = data.get_combined_data_by_variable(key)[['key.projectId', 'key.userId', 'key.sourceId', 'value.time',
+                                        'value.timeCompleted', 'value.timeNotification', 'value.name']]
+        df_ques_app_event = pd.concat(all_ques_list.values()).reset_index(drop=True)
+        df_ques_app_event['value.time'] = pd.to_datetime(df_ques_app_event['value.time'], unit="s")
+        df_ques_app_event['value.timeNotification'] = pd.to_datetime(df_ques_app_event['value.timeNotification'], unit="s")
+        df_ques_app_event['value.timeCompleted'] = pd.to_datetime(df_ques_app_event['value.timeCompleted'], unit="s")
+        df_ques_app_event = df_ques_app_event.rename({"key.userId" : "uid", "value.time" : "time", "value.timeNotification": "time_notification",
+                                                            "value.timeCompleted": "time_completed", "value.name":"name"}, axis=1)
+        df_ques_app_event = df_ques_app_event.drop_duplicates(subset=["uid", "time", "name"]).reset_index(drop=True)
+        df_ques_app_event["date"] = df_ques_app_event["time"].dt.date
+        df_ques_app_event = df_ques_app_event.sort_values(by=["uid", "time_notification", "time_completed"]).reset_index(drop=True)
+        return df_ques_app_event
+
+    def compute_features(self, data: RadarData) -> RadarData:
+        """
+        compute and combine the features for each feature in the group.
+        """
+        pass
+
+class QuestionnaireNotificationResponseLatency(Feature):
+    def __init__(self):
+        self.name = "QuestionnaireNotificationResponseLatency"
+        self.description = "The time it took for participants to start filling out the questionnaires after receiving the notification."
+        self.required_input_data = ["questionnaire_ari_self", "questionnaire_gad7", "questionnaire_phq8", "questionnaire_rpq", "questionnaire_baars_iv"]
+
+    def preprocess(self, data):
+        """
+        Preprocess the data for each feature in the group.
+        """
+        return data
+
+    def calculate(self, data) -> float:
+        df_ques_app_event = data
+        df_ques_app_event_summary = df_ques_app_event.groupby(["uid", "time_notification"]).agg({"time": min, "time_completed":max}).reset_index().rename({"time":"start_time", "time_completed":"finished_time"}, axis=1)
+        df_ques_app_event_summary["notification_response_time"] = df_ques_app_event_summary["start_time"] - df_ques_app_event_summary["time_notification"]
+        df_ques_app_event_summary["total_completion_time"] = df_ques_app_event_summary["finished_time"] - df_ques_app_event_summary["time_notification"]
+        df_ques_app_event_summary["notification_response_time_sec"] = df_ques_app_event_summary["notification_response_time"].dt.total_seconds()
+        return df_ques_app_event_summary
+
+
+
+
+class QuestionnaireCompletionTime(Feature):
+    def __init__(self):
+        self.name = "QuestionnaireCompletionTime"
+        self.description = "The time it took for participants to finish the questionnaires after starting them. "
+        self.required_input_data = ["questionnaire_ari_self", "questionnaire_gad7", "questionnaire_phq8", "questionnaire_rpq", "questionnaire_baars_iv"]
+
+    def preprocess(self, data):
+        """
+        Preprocess the data for each feature in the group.
+        """
+        return data
+
+    def calculate(self, data) -> float:
+        df_ques_app_event = data
+        df_ques_app_event_summary = df_ques_app_event.groupby(["uid", "time_notification"]).agg({"time": min, "time_completed":max}).reset_index().rename({"time":"start_time", "time_completed":"finished_time"}, axis=1)
+        df_ques_app_event_summary["questionnaire_completion_time"] = df_ques_app_event_summary["finished_time"] - df_ques_app_event_summary["start_time"]
+        df_ques_app_event_summary["questionnaire_completion_time_sec"] = df_ques_app_event_summary["questionnaire_completion_time"].dt.total_seconds()
+        return df_ques_app_event_summary