bright1 commited on
Commit
6f4e733
·
1 Parent(s): 248f611

removed code that depends on tabulate

Browse files
Files changed (1) hide show
  1. src/app/app.py +8 -3
src/app/app.py CHANGED
@@ -23,7 +23,7 @@ DIRPATH = os.path.dirname(os.path.realpath(__file__))
23
  # set path for ml files
24
  ml_contents_path = os.path.join(DIRPATH, '..', 'assets', 'ml_components', 'toolkit_folder')
25
 
26
-
27
  ml_contents = load_file(ml_contents_path)
28
 
29
  Encoder = ml_contents["OneHotEncoder"]
@@ -32,6 +32,8 @@ features_ = ml_contents['feature_names']
32
 
33
 
34
 
 
 
35
  @app.get('/')
36
  def root():
37
  return 'Welcome to the Gorecery Sales Forecasting API'
@@ -44,6 +46,7 @@ def check_health():
44
  async def predict_sales( store_id: int, category_id: int, onpromotion: int,
45
  city: str, store_type: int, cluster: int, date_: Annotated[datetime.date, "The date of sales"] = datetime.date.today()):
46
 
 
47
  input = {
48
  'store_id':[store_id],
49
  'category_id':[category_id],
@@ -54,10 +57,12 @@ async def predict_sales( store_id: int, category_id: int, onpromotion: int,
54
  'date_': [date_]
55
  }
56
 
 
57
  input_data = pd.DataFrame(input)
58
  date_extracts(input_data)
59
- print(f'INFO: {input_data.to_markdown()}')
60
-
 
61
  sales = make_predcition(Encoder, model, input)
62
  sales_value = float(sales[0])
63
  return {'sales': sales_value}
 
23
  # set path for ml files
24
  ml_contents_path = os.path.join(DIRPATH, '..', 'assets', 'ml_components', 'toolkit_folder')
25
 
26
+ # get contents
27
  ml_contents = load_file(ml_contents_path)
28
 
29
  Encoder = ml_contents["OneHotEncoder"]
 
32
 
33
 
34
 
35
+ # define endpoints
36
+
37
  @app.get('/')
38
  def root():
39
  return 'Welcome to the Gorecery Sales Forecasting API'
 
46
  async def predict_sales( store_id: int, category_id: int, onpromotion: int,
47
  city: str, store_type: int, cluster: int, date_: Annotated[datetime.date, "The date of sales"] = datetime.date.today()):
48
 
49
+ # create a dictionary of inputs
50
  input = {
51
  'store_id':[store_id],
52
  'category_id':[category_id],
 
57
  'date_': [date_]
58
  }
59
 
60
+ # convert to dataframe and extract datetime features
61
  input_data = pd.DataFrame(input)
62
  date_extracts(input_data)
63
+
64
+
65
+ # make prediction
66
  sales = make_predcition(Encoder, model, input)
67
  sales_value = float(sales[0])
68
  return {'sales': sales_value}