Spaces:
Sleeping
Sleeping
File size: 4,098 Bytes
279c335 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 | from flask import Flask, request, jsonify
import joblib, pandas as pd, os
childcare_api = Flask(__name__)
MODEL_PATH = "xgb_tuned_model.joblib"
model = joblib.load(MODEL_PATH)
# ── Validation constants ──────────────────────────────────────
VALID_CARE_PROGRAM = {"Full Day", "Half Day", "After School"}
VALID_FACILITY_SIZE = {"Small", "Medium", "Large"}
VALID_CITY_TYPE = {"Tier 1", "Tier 2", "Tier 3"}
VALID_FACILITY_TYPE = {"Full-Service Center", "Montessori School", "Home Daycare", "Corporate Daycare"}
VALID_CHILD_ID_CHAR = {"FD", "HD", "AS"}
VALID_ACTIVITY_CAT = {"Academic", "Creative", "Wellness"}
REQUIRED_FIELDS = [
"Child_Age_Months", "Child_Care_Program", "Child_Attendance_Rate",
"Child_Monthly_Fee", "Facility_Size", "Facility_Location_City_Type",
"Facility_Type", "Child_Id_char", "Facility_Establishment_Year",
"Activity_Type_Category",
]
def validate_input(data):
# 1. Check required fields
missing = [f for f in REQUIRED_FIELDS if f not in data]
if missing:
return False, f"Missing required fields: {missing}"
# 2. Type checks
try:
float(data["Child_Age_Months"])
float(data["Child_Attendance_Rate"])
float(data["Child_Monthly_Fee"])
int(data["Facility_Establishment_Year"])
except (ValueError, TypeError) as e:
return False, f"Type error: {e}"
# 3. Range checks
if not (0 <= float(data["Child_Age_Months"]) <= 120):
return False, "Child_Age_Months must be between 0 and 120"
if not (0.0 <= float(data["Child_Attendance_Rate"]) <= 1.0):
return False, "Child_Attendance_Rate must be between 0.0 and 1.0"
if not (0 <= float(data["Child_Monthly_Fee"]) <= 10000):
return False, "Child_Monthly_Fee must be between 0 and 10000"
# 4. Categorical checks
if data["Child_Care_Program"] not in VALID_CARE_PROGRAM:
return False, f"Child_Care_Program must be one of {VALID_CARE_PROGRAM}"
if data["Facility_Size"] not in VALID_FACILITY_SIZE:
return False, f"Facility_Size must be one of {VALID_FACILITY_SIZE}"
if data["Facility_Location_City_Type"] not in VALID_CITY_TYPE:
return False, f"Facility_Location_City_Type must be one of {VALID_CITY_TYPE}"
if data["Facility_Type"] not in VALID_FACILITY_TYPE:
return False, f"Facility_Type must be one of {VALID_FACILITY_TYPE}"
if data["Child_Id_char"] not in VALID_CHILD_ID_CHAR:
return False, f"Child_Id_char must be one of {VALID_CHILD_ID_CHAR}"
if data["Activity_Type_Category"] not in VALID_ACTIVITY_CAT:
return False, f"Activity_Type_Category must be one of {VALID_ACTIVITY_CAT}"
return True, None
@childcare_api.get("/health")
def health():
return jsonify({"status": "healthy", "model": "XGBoost ChildCare Revenue Pipeline"})
@childcare_api.post("/v1/predict")
def predict_revenue():
data = request.get_json(force=True)
is_valid, error_msg = validate_input(data)
if not is_valid:
return jsonify({"error": error_msg}), 400
input_df = pd.DataFrame([{
"Child_Age_Months": float(data["Child_Age_Months"]),
"Child_Care_Program": data["Child_Care_Program"],
"Child_Attendance_Rate": float(data["Child_Attendance_Rate"]),
"Child_Monthly_Fee": float(data["Child_Monthly_Fee"]),
"Facility_Size": data["Facility_Size"],
"Facility_Location_City_Type": data["Facility_Location_City_Type"],
"Facility_Type": data["Facility_Type"],
"Child_Id_char": data["Child_Id_char"],
"Facility_Establishment_Year": int(data["Facility_Establishment_Year"]),
"Activity_Type_Category": data["Activity_Type_Category"],
}])
prediction = float(model.predict(input_df)[0])
return jsonify({"Revenue": round(prediction, 2)}), 200
if __name__ == "__main__":
port = int(os.environ.get("PORT", 7860))
childcare_api.run(host="0.0.0.0", port=port)
|