train.py

import joblib

from sklearn.datasets import fetch_openml

from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer

from sklearn.pipeline import make_pipeline

from sklearn.model_selection import train_test_split, RandomizedSearchCV

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from warnings import filterwarnings
filterwarnings('ignore')

df = pd.read_csv("/content/forest_health_data_with_target.csv")


target = 'Health_Status'
numeric_features = [
    'Latitude',
    'Longitude',
    'DBH',
    'Tree_Height',
    'Crown_Width_North_South',
    'Crown_Width_East_West',
    'Slope',
    'Elevation',
    'Temperature',
    'Humidity',
    'Soil_TN',
    'Soil_TP',
    'Soil_AP',
    'Soil_AN',
    'Menhinick_Index',
    'Gleason_Index',
    'Fire_Risk_Index'
    
]




print("Creating data subsets")

X = df[numeric_features]
y = df[target]

Xtrain, Xtest, ytrain, ytest = train_test_split(
    X, y,
    test_size=0.2,
    random_state=42
)

preprocessor = make_column_transformer(
    (StandardScaler(), numeric_features),    
)

model_logistic_regression = LogisticRegression(n_jobs=-1)

print("Estimating Best Model Pipeline")

model_pipeline = make_pipeline(
    preprocessor,
    model_logistic_regression
)

param_distribution = {
    "logisticregression__C": [0.001, 0.01, 0.1, 0.5, 1]
}

rand_search_cv = RandomizedSearchCV(
    model_pipeline,
    param_distribution,
    n_iter=3,
    cv=3,
    random_state=42
)

rand_search_cv.fit(Xtrain, ytrain)

print("Logging Metrics")
print(f"Accuracy: {rand_search_cv.best_score_}")

print("Serializing Model")

saved_model_path = "model.joblib"

joblib.dump(rand_search_cv.best_estimator_, saved_model_path)