ml-api/main.py at main · projects-mk/ml-api · GitHub

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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
from fastapi import FastAPI
import pandas as pd
from otomoto.model_predictions import Predictor
from otomoto.input_models import OtomotoInputData
from fastapi import Body
from utils import generate_conn_string
from fastapi.middleware.cors import CORSMiddleware
import os

app = FastAPI(title=os.getenv("APP_NAME"), version=os.getenv("APP_VERSION"))

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)


@app.get("/api/v1/otomoto/", tags=["otomoto"])
async def otomoto_marka():
    try:
        marka = "SELECT DISTINCT marka FROM otomoto.preprocessed"
        options = sorted(
            pd.read_sql_query(marka, con=generate_conn_string("projects"))[
                "marka"
            ].values
        )
        return {"response": options}

    except Exception as e:
        return {"response": str(e)}


@app.get("/api/v1/otomoto/{marka}", tags=["otomoto"])
async def otomoto_dropdown_values(marka: str):
    try:
        model = (
            f"SELECT DISTINCT model FROM otomoto.preprocessed WHERE marka = '{marka}'"
        )
        model = sorted(
            pd.read_sql_query(model, con=generate_conn_string("projects"))[
                "model"
            ].values
        )

        rodzaj_paliwa = "SELECT DISTINCT rodzaj_paliwa FROM otomoto.preprocessed"
        rodzaj_paliwa = sorted(
            pd.read_sql_query(rodzaj_paliwa, con=generate_conn_string("projects"))[
                "rodzaj_paliwa"
            ].values
        )

        skrzynia_biegow = "SELECT DISTINCT skrzynia_biegow FROM otomoto.preprocessed"
        skrzynia_biegow = sorted(
            pd.read_sql_query(skrzynia_biegow, con=generate_conn_string("projects"))[
                "skrzynia_biegow"
            ]
            .dropna()
            .values
        )

        naped = "SELECT DISTINCT naped FROM otomoto.preprocessed"
        naped = sorted(
            pd.read_sql_query(naped, con=generate_conn_string("projects"))["naped"]
            .dropna()
            .values
        )

        nadwozie = "SELECT DISTINCT nadwozie FROM otomoto.preprocessed"
        nadwozie = sorted(
            pd.read_sql_query(nadwozie, con=generate_conn_string("projects"))[
                "nadwozie"
            ]
            .dropna()
            .values
        )

        bezwypadkowy = "SELECT DISTINCT bezwypadkowy FROM otomoto.preprocessed"
        bezwypadkowy = sorted(
            pd.read_sql_query(bezwypadkowy, con=generate_conn_string("projects"))[
                "bezwypadkowy"
            ]
            .dropna()
            .values
        )

        serwisowany_w_aso = (
            "SELECT DISTINCT serwisowany_w_aso FROM otomoto.preprocessed"
        )
        serwisowany_w_aso = sorted(
            pd.read_sql_query(serwisowany_w_aso, con=generate_conn_string("projects"))[
                "serwisowany_w_aso"
            ]
            .dropna()
            .values
        )

        stan = "SELECT DISTINCT stan FROM otomoto.preprocessed"
        stan = sorted(
            pd.read_sql_query(stan, con=generate_conn_string("projects"))["stan"]
            .dropna()
            .values
        )

        return {
            "response": {
                "model": model,
                "rodzaj_paliwa": rodzaj_paliwa,
                "skrzynia_biegow": skrzynia_biegow,
                "naped": naped,
                "nadwozie": nadwozie,
                "bezwypadkowy": bezwypadkowy,
                "serwisowany_w_aso": serwisowany_w_aso,
                "stan": stan,
            }
        }

    except Exception as e:
        return {"response": str(e)}


@app.post("/api/v1/otomoto/predict", tags=["model_predictions"])
async def otomoto_predict(data: OtomotoInputData = Body(...)):

    try:
        transformer_name = "otomoto_car_price_predictor_data_encoder"
        model_name = "xgboost_otomoto_car_price_predictor_price_predictor"
        vars_to_ohe = [
            "marka",
            "model",
            "rodzaj_paliwa",
            "skrzynia_biegow",
            "naped",
            "nadwozie",
            "bezwypadkowy",
            "serwisowany_w_aso",
            "stan",
        ]

        predictor = Predictor(model_name=model_name, transformer_name=transformer_name)
        predictor.load_models()

        data = data.model_dump()
        response = predictor.predict(data, vars_to_ohe)

        return {"response": float(response)}

    except Exception as e:
        return {"response": str(e)}