improved api alarm endpoint

ml/src/analysis/evaluate_balance.py

@@ -70,4 +70,4 @@ def main():
                 writer.writerow(data)
 
 if __name__ == '__main__':
-    main()
\ No newline at end of file
+    main()

ml/src/analysis/evaluate_gender_bias.py

@@ -260,4 +260,4 @@ def main():
     plt.show()
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()

ml/src/analysis/evaluate_preprocessing.py

@@ -136,4 +136,4 @@ def main():
                         writer.writerow(data)
 
 if __name__ == '__main__':
-    main()
\ No newline at end of file
+    main()

ml/src/analysis/evaluate_survival_case.py

@@ -8,8 +8,8 @@ import paths as pt
 from tools import data_loader
 from utility.config import load_config
 from utility.data import write_csv
-from sksurv.ensemble import GradientBoostingSurvivalAnalysis
 from sklearn.model_selection import KFold
+from sksurv.ensemble import GradientBoostingSurvivalAnalysis
 from sksurv.metrics import (concordance_index_censored,
                             concordance_index_ipcw,
                             integrated_brier_score)

ml/src/analysis/find_best_ats_resolution.py

@@ -113,4 +113,4 @@ def main():
                     bbox_inches = "tight")
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()

ml/src/api/main.py

@@ -11,15 +11,16 @@ import csv
 import joblib
 import yaml
 import pandas as pd
+import numpy as np
 from typing import Optional
 from fastapi import Depends, FastAPI, HTTPException, Request
 from fastapi.responses import JSONResponse
 from fastapi_jwt_auth import AuthJWT
 from fastapi_jwt_auth.exceptions import AuthJWTException
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
-from fastapi import Request, HTTPException
 from sksurv.ensemble import GradientBoostingSurvivalAnalysis
 from xgboost import XGBClassifier
+from decimal import Decimal
 
 app = FastAPI(title='AIR API', version='1.0',
               description='An API that classifies citizens based on data')
@@ -88,7 +89,7 @@ class TrainingOutputData(pydantic.BaseModel):
 
 @app.get('/')
 def index():
-    return {'message': f'AIR API v. 0.1'}
+    return {'message': 'AIR API v. 0.1'}
 
 @app.get('/user', dependencies=[Depends(JWTBearer())], tags=["login"])
 def user(Authorize: AuthJWT = Depends()):
@@ -139,10 +140,12 @@ def predict_alarm(incoming_data: InputData):
     df_for_alarm = add_embedding(df.copy(), 'alarm', ats_resolution)
     surv_func = alarm_model.predict_survival_function(df_for_alarm)
 
-    event_times = [int(x) for x in surv_func[0].x]
-    surv_probs = [float(x) for x in surv_func[0].y]
-
-    prob_after_one_year = 1 - surv_probs[365*5]
+    event_times = list(range(1, 13))
+    surv_probs = np.array([float(x) for x in surv_func[0].y][:360])
+    surv_probs = np.mean(surv_probs.reshape(-1, 30), axis=1)
+    surv_probs = list(map((lambda x: float(round(100*Decimal(x), 1))), surv_probs))
+    
+    prob_after_one_year = 100 - surv_probs[-1]
     alarm_arguments = generate_alarm_arguments(df, ats_resolution, prob_after_one_year)
 
     return {
@@ -159,8 +162,8 @@ def predict_training(incoming_data: InputData):
     data = validate_data(incoming_data)
     df = prepare_data(data, ats_resolution)
 
-    complete_model = read_xgb_model(f'complete_xgboost.joblib')
-    compliance_model = read_xgb_model(f'compliance_xgboost.joblib')
+    complete_model = read_xgb_model('complete_xgboost.joblib')
+    compliance_model = read_xgb_model('compliance_xgboost.joblib')
 
     df_for_complete = add_embedding(df.copy(), 'complete', ats_resolution)
     df_for_compliance = add_embedding(df.copy(), 'compliance', ats_resolution)
@@ -264,7 +267,7 @@ def generate_alarm_arguments(df: pd.DataFrame,
         arguments.append(loan_period_argument)
 
     arguments.append("får efter et år en nødalarm")
-    arguments.append(f"med {round(prob_after_one_year*100, 1)}% sandsynlighed")
+    arguments.append(f"med {round(prob_after_one_year, 1)}% sandsynlighed")
     return arguments
 
 def load_settings(file_name):

ml/src/data/make_dataset_count.py

@@ -68,4 +68,4 @@ def main():
         write_csv(df, file_path, file_name)
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()

ml/src/data/make_dataset_ohe.py

@@ -51,4 +51,4 @@ def main():
         write_csv(df, file_path, file_name)
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()

ml/src/data/make_dataset_ordinal.py

@@ -61,4 +61,4 @@ def main():
         write_csv(df, file_path, file_name)
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()

ml/src/model/train_alarm_model.py

@@ -31,7 +31,7 @@ def main():
     model.fit(X, y)
 
     file_path = pt.MODELS_DIR
-    file_name = f'alarm_gradboost.joblib'
+    file_name = 'alarm_gradboost.joblib'
     with open(Path.joinpath(file_path, file_name), 'wb') as fd:
         outfile = BytesIO()
         file_writer.write_joblib(model, outfile)

ml/src/model/train_complete_model.py

@@ -38,7 +38,7 @@ def main():
     model.fit(X, y)
 
     file_path = pt.MODELS_DIR
-    file_name = f'complete_xgboost.joblib'
+    file_name = 'complete_xgboost.joblib'
     with open(Path.joinpath(file_path, file_name), 'wb') as fd:
         outfile = BytesIO()
         file_writer.write_joblib(model, outfile)

ml/src/model/train_compliance_model.py

@@ -38,7 +38,7 @@ def main():
     model.fit(X, y)
 
     file_path = pt.MODELS_DIR
-    file_name = f'compliance_xgboost.joblib'
+    file_name = 'compliance_xgboost.joblib'
     with open(Path.joinpath(file_path, file_name), 'wb') as fd:
         outfile = BytesIO()
         file_writer.write_joblib(model, outfile)

ml/src/tools/data_loader.py

@@ -8,10 +8,11 @@ from abc import ABC, abstractmethod
 from sklearn.model_selection import train_test_split
 from typing import Tuple, List
 from pathlib import Path
-from io import BytesIO, StringIO
+from io import StringIO
 import shutil
 from tools import file_reader, preprocessor
 import numpy as np
+import pandas as pd
 
 class BaseDataLoader(ABC):
     """
@@ -20,22 +21,22 @@ class BaseDataLoader(ABC):
     def __init__(self,
                  file_path: Path,
                  file_name: str,
-                 settings,
-                 converters=None):
+                 settings: dict,
+                 converters: dict = None):
         """Initilizer method that takes a file path, file name,
         settings and optionally a converter"""
-        self.X = None
-        self.y = None
-        self.file_path = file_path
-        self.file_name = file_name
-        self.settings = settings
-        self.converters = converters
+        self.X: pd.DataFrame = None
+        self.y: np.ndarray = None
+        self.file_path: Path = file_path
+        self.file_name: str = file_name
+        self.settings: dict = settings
+        self.converters: dict = converters
 
     @abstractmethod
-    def load_data(self):
+    def load_data(self) -> None:
         """Loads the data from a data set at startup"""
 
-    def get_data(self):
+    def get_data(self) -> Tuple[pd.DataFrame, np.ndarray]:
         """
         This method returns the features and targets
         :return: X and y
@@ -104,8 +105,8 @@ class CompleteDataLoader(BaseDataLoader):
             df = file_reader.read_csv(infile, converters=self.converters)
         X = df.drop(['Complete'], axis=1)
         y = df['Complete']
-        self.X = X
-        self.y = y
+        self.X = pd.DataFrame(X)
+        self.y = np.array(y)
         return self
 
 class ComplianceDataLoader(BaseDataLoader):
@@ -121,8 +122,8 @@ class ComplianceDataLoader(BaseDataLoader):
             df = file_reader.read_csv(infile, converters=self.converters)
         X = df.drop(['Compliance'], axis=1)
         y = df['Compliance']
-        self.X = X
-        self.y = y
+        self.X = pd.DataFrame(X)
+        self.y = np.array(y)
         return self
 
 class FallDataLoader(BaseDataLoader):
@@ -138,8 +139,8 @@ class FallDataLoader(BaseDataLoader):
             df = file_reader.read_csv(infile, converters=self.converters)
         X = df.drop(['Fall'], axis=1)
         y = df['Fall']
-        self.X = X
-        self.y = y
+        self.X = pd.DataFrame(X)
+        self.y = np.array(y)
         return self
 
 class RiskDataLoader(BaseDataLoader):
@@ -155,8 +156,8 @@ class RiskDataLoader(BaseDataLoader):
             df = file_reader.read_csv(infile, converters=self.converters)
         X = df.drop(['Risk'], axis=1)
         y = df['Risk']
-        self.X = X
-        self.y = y
+        self.X = pd.DataFrame(X)
+        self.y = np.array(y)
         return self
 
 class AlarmDataLoader(BaseDataLoader):
@@ -173,6 +174,6 @@ class AlarmDataLoader(BaseDataLoader):
         X = df.drop(['Status', 'Days'], axis=1)
         y = np.array(list(tuple(x) for x in df[['Status', 'Days']].to_numpy()),
                      dtype=[('Status', 'bool'), ('Days_to_alarm', '>i4')])
-        self.X = X
-        self.y = y
+        self.X = pd.DataFrame(X)
+        self.y = np.array(y)
         return self
\ No newline at end of file