app/modelling.py

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):
    df=dataset.copy()
    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)

    return {"model":model,
            "encoder":encoder,
            "transform":transform,
            "Accuracy":f"{accuracy_score(y_test,predict):4f}",
            "F1_Score":f"{f1_score(y_test,predict):4f}"}