Spaces:
Sleeping
Sleeping
File size: 5,406 Bytes
f15767b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
#!/usr/bin/env python
# encoding: utf-8
from fastapi import FastAPI, Form, Depends
from pydantic import BaseModel
import numpy as np
import pandas as pd
from xgboost import XGBRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import RobustScaler
from skforecast.ForecasterAutoreg import ForecasterAutoreg
from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error
import joblib
app = FastAPI()
class Msg(BaseModel):
msg: str
class RetrainRequest(BaseModel):
lag: int
differentiation: str
transformer: str
externalTransformation: str
test_size: int
class PredictRequest(BaseModel):
steps: int
test_size: int
externalTransformation: str
@app.get("/welcomeMessage")
async def welcome():
return {"message": "Hello World. Welcome to FastAPI!"}
@app.get("/")
async def root():
return {"message": "Hello World"}
def form_retrain(lag: str = Form(...), differentiation: str = Form(...), transformer: str = Form(...), externalTransformation: str = Form (...), test_size: str = Form(...)):
return RetrainRequest(lag=int(lag), differentiation=str(differentiation), transformer=transformer, externalTransformation=externalTransformation, test_size=int(test_size))
def form_prediction(steps: str = Form(...), externalTransformation: str = Form (...), test_size: str = Form(...)):
return PredictRequest(steps=int(steps), externalTransformation=externalTransformation, test_size=int(test_size))
def apply_transformation(data, transform_type):
if transform_type == 'Log':
return np.log1p(data)
elif transform_type == 'Square Root':
return np.sqrt(data)
else:
return data
def reverse_transformation(transformed_data, transform_type):
if transform_type == 'Log':
return np.expm1(transformed_data)
elif transform_type == 'Square Root':
return np.square(transformed_data)
else:
return transformed_data
@app.post("/retrain")
async def retrain(requess: RetrainRequest = Depends(form_retrain), test_size: int = 3):
with open('ammonia_market_monthly_avg_new.xlsx', 'rb') as file:
df = pd.read_excel(file)
df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d')
df.set_index('date', inplace=True)
lags = requess.lag
differentiation = requess.differentiation
if differentiation == "0":
differentiation = None
else:
differentiation = int(differentiation)
transformer_y = requess.transformer
test_size = requess.test_size
externalTransformation=requess.externalTransformation
target_column = 'southeast_asia'
train = df.iloc[:-(test_size)]
test = df.iloc[-(test_size):]
train_transformed = apply_transformation(train[target_column], externalTransformation)
if transformer_y == 'StandardScaler':
transformer_y = StandardScaler()
elif transformer_y == 'MinMaxScaler':
transformer_y = MinMaxScaler()
elif transformer_y == 'RobustScaler':
transformer_y = RobustScaler()
else:
transformer_y = None
forecaster = ForecasterAutoreg(
regressor = XGBRegressor(random_state=123),
lags = lags,
differentiation = differentiation,
transformer_y = transformer_y
)
forecaster.fit(y=train_transformed)
predictions = forecaster.predict(steps=test_size)
pred = reverse_transformation(predictions, externalTransformation)
df_reset = df.reset_index()
last_date = df_reset.iloc[-(test_size)]['date']
months_ahead = pd.date_range(last_date, periods=test_size, freq='M')
preds = round(pred, 2).tolist()
actual = test[target_column]
date_value_pairs = dict(zip(months_ahead.tolist(), preds))
rmse = np.sqrt(mean_squared_error(actual, preds))
mape = mean_absolute_percentage_error(actual, preds)
joblib.dump(forecaster, filename='forecaster_new.py')
return {
'predictions': date_value_pairs,
'actual': actual,
'rmse': rmse,
'mape': mape
}
@app.post("/predict")
async def predict(requess: PredictRequest = Depends(form_prediction), steps: int = 3, externalTransformation: str = "None", test_size: int = 3):
try:
with open('forecaster_new.py', 'rb') as file:
forecaster_southeast = joblib.load(file)
except FileNotFoundError:
forecaster_southeast = joblib.load('forecaster_southeast.py')
try:
with open('ammonia_market_monthly_avg_new.xlsx', 'rb') as file:
df = pd.read_excel(file)
except FileNotFoundError:
df = pd.read_excel('ammonia_market_monthly_avg_2010_2020.xlsx')
df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d')
df.set_index('date', inplace=True)
steps = requess.steps
test_size = requess.test_size
predictions = forecaster_southeast.predict(steps=steps)
pred = reverse_transformation(predictions, requess.externalTransformation)
preds = round(pred, 2).tolist()
df_reset = df.reset_index()
last_date = df_reset.iloc[-(test_size)]['date']
months_ahead = pd.date_range(last_date, periods=steps, freq='M')
date_value_pairs = dict(zip(months_ahead.tolist(), preds))
return {
"steps": steps,
"predictions": date_value_pairs
}
|