File size: 1,979 Bytes
9248464 |
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 |
import os
import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import PowerTransformer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import f1_score
import argparse
import joblib
def train(dataset_pth):
df=pd.read_csv(dataset_pth)
features=["Torque(Nm)","Hydraulic_Pressure(bar)","Cutting(kN)","Coolant_Pressure(bar)","Spindle_Speed(RPM)","Coolant_Temperature","Downtime"]
df=df[features]
df.dropna(inplace=True,ignore_index=True)
X=df.drop("Downtime",axis=1)
y=df["Downtime"]
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.20,random_state=42,stratify=y)
transform=PowerTransformer()
X_train=transform.fit_transform(X_train)
X_test=transform.transform(X_test)
encoder=LabelEncoder()
y_train=encoder.fit_transform(y_train)
y_test=encoder.transform(y_test)
model=RandomForestClassifier(random_state=42)
model.fit(X_train,y_train)
predict=model.predict(X_test)
cwd=os.getcwd()
transform_pth=os.path.join(cwd,"app","transform.pkl")
encoder_pth=os.path.join(cwd,"app","encoder.pkl")
model_pth=os.path.join(cwd,"app","model.pkl")
joblib.dump(transform,transform_pth)
joblib.dump(encoder,encoder_pth)
joblib.dump(model,model_pth)
return {"Accuracy":accuracy_score(y_test,predict),
"F1_Score":f1_score(y_test,predict)}
if __name__=="__main__":
parser=argparse.ArgumentParser()
parser.add_argument("--dataset_pth",default="/home/sudhanshu/manufacturing_defect/Manufacturing_Downtime_Dataset.csv")
args=parser.parse_args()
results=train(args.dataset_pth)
print(f"Accuracy: {results['Accuracy']}\n")
print(f"F1_Score: {results['F1_Score']}")
|