Spaces:
Runtime error
Runtime error
Upload folder using huggingface_hub
Browse files- data/engine_data.csv +0 -0
- data/test.csv +0 -0
- data/train.csv +0 -0
- hosting/hosting.py +34 -0
- model_building/data_register.py +148 -0
- model_building/model_experiment.py +122 -0
- model_building/model_registration.py +128 -0
- model_building/prep.py +145 -0
- models/best_model.pkl +3 -0
- models/best_params.json +8 -0
- models/feature_importance.csv +7 -0
- models/final_metrics.json +6 -0
- models/model_comparison_matrix.csv +5 -0
- models/model_specs.json +5 -0
- requirements.txt +1 -1
data/engine_data.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data/test.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data/train.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hosting/hosting.py
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from huggingface_hub import login, upload_folder
|
| 2 |
+
import os
|
| 3 |
+
|
| 4 |
+
# ==========================================
|
| 5 |
+
# HF TOKEN
|
| 6 |
+
# ==========================================
|
| 7 |
+
|
| 8 |
+
HF_TOKEN = os.getenv("HF_TOKEN")
|
| 9 |
+
|
| 10 |
+
if not HF_TOKEN:
|
| 11 |
+
raise Exception("HF_TOKEN not found")
|
| 12 |
+
|
| 13 |
+
HF_TOKEN = HF_TOKEN.strip()
|
| 14 |
+
|
| 15 |
+
print("HF Token Loaded Successfully")
|
| 16 |
+
|
| 17 |
+
# ==========================================
|
| 18 |
+
# LOGIN
|
| 19 |
+
# ==========================================
|
| 20 |
+
|
| 21 |
+
login(token=HF_TOKEN)
|
| 22 |
+
|
| 23 |
+
# ==========================================
|
| 24 |
+
# UPLOAD TO HUGGING FACE SPACE
|
| 25 |
+
# ==========================================
|
| 26 |
+
|
| 27 |
+
upload_folder(
|
| 28 |
+
repo_id="vyasmax9/predictive-maintenance",
|
| 29 |
+
folder_path="Predictive_Maintenance",
|
| 30 |
+
repo_type="space",
|
| 31 |
+
token=HF_TOKEN
|
| 32 |
+
)
|
| 33 |
+
|
| 34 |
+
print("Deployment Uploaded Successfully")
|
model_building/data_register.py
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from huggingface_hub import (
|
| 2 |
+
HfApi,
|
| 3 |
+
create_repo,
|
| 4 |
+
login
|
| 5 |
+
)
|
| 6 |
+
|
| 7 |
+
from huggingface_hub.utils import RepositoryNotFoundError
|
| 8 |
+
|
| 9 |
+
import os
|
| 10 |
+
|
| 11 |
+
# ==========================================
|
| 12 |
+
# CONFIGURATION
|
| 13 |
+
# ==========================================
|
| 14 |
+
|
| 15 |
+
DATA_PATH = os.path.join(
|
| 16 |
+
os.getcwd(),
|
| 17 |
+
"Predictive_Maintenance",
|
| 18 |
+
"data"
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
repo_id = "vyasmax9/predictive-maintenance-engine"
|
| 22 |
+
repo_type = "dataset"
|
| 23 |
+
|
| 24 |
+
# ==========================================
|
| 25 |
+
# TOKEN CHECK
|
| 26 |
+
# ==========================================
|
| 27 |
+
|
| 28 |
+
TOKEN = os.getenv("HF_TOKEN")
|
| 29 |
+
|
| 30 |
+
if not TOKEN:
|
| 31 |
+
raise Exception("HF_TOKEN not found")
|
| 32 |
+
|
| 33 |
+
# Remove hidden spaces/newlines
|
| 34 |
+
TOKEN = TOKEN.strip()
|
| 35 |
+
|
| 36 |
+
print("Token Found:", TOKEN is not None)
|
| 37 |
+
print("Token Length:", len(TOKEN))
|
| 38 |
+
print("Token Prefix:", TOKEN[:3])
|
| 39 |
+
|
| 40 |
+
# ==========================================
|
| 41 |
+
# LOGIN TO HUGGING FACE
|
| 42 |
+
# ==========================================
|
| 43 |
+
|
| 44 |
+
login(token=TOKEN)
|
| 45 |
+
|
| 46 |
+
api = HfApi()
|
| 47 |
+
|
| 48 |
+
# ==========================================
|
| 49 |
+
# DEBUG INFORMATION
|
| 50 |
+
# ==========================================
|
| 51 |
+
|
| 52 |
+
print("Current Directory:", os.getcwd())
|
| 53 |
+
print("Data Path:", DATA_PATH)
|
| 54 |
+
print("Path Exists:", os.path.exists(DATA_PATH))
|
| 55 |
+
|
| 56 |
+
# ==========================================
|
| 57 |
+
# CHECK DATA FOLDER
|
| 58 |
+
# ==========================================
|
| 59 |
+
|
| 60 |
+
if not os.path.exists(DATA_PATH):
|
| 61 |
+
raise Exception(
|
| 62 |
+
f"Path not found: {DATA_PATH}"
|
| 63 |
+
)
|
| 64 |
+
|
| 65 |
+
# ==========================================
|
| 66 |
+
# CREATE DATASET REPOSITORY
|
| 67 |
+
# ==========================================
|
| 68 |
+
|
| 69 |
+
try:
|
| 70 |
+
|
| 71 |
+
api.repo_info(
|
| 72 |
+
repo_id=repo_id,
|
| 73 |
+
repo_type=repo_type
|
| 74 |
+
)
|
| 75 |
+
|
| 76 |
+
print(
|
| 77 |
+
f"Dataset Repo '{repo_id}' already exists."
|
| 78 |
+
)
|
| 79 |
+
|
| 80 |
+
except RepositoryNotFoundError:
|
| 81 |
+
|
| 82 |
+
print(
|
| 83 |
+
"Creating Dataset Repository..."
|
| 84 |
+
)
|
| 85 |
+
|
| 86 |
+
create_repo(
|
| 87 |
+
repo_id=repo_id,
|
| 88 |
+
repo_type=repo_type,
|
| 89 |
+
private=False,
|
| 90 |
+
token=TOKEN
|
| 91 |
+
)
|
| 92 |
+
|
| 93 |
+
print(
|
| 94 |
+
"Dataset Repository Created"
|
| 95 |
+
)
|
| 96 |
+
|
| 97 |
+
except Exception as e:
|
| 98 |
+
|
| 99 |
+
print(
|
| 100 |
+
f"Repository Check Error: {e}"
|
| 101 |
+
)
|
| 102 |
+
raise
|
| 103 |
+
|
| 104 |
+
# ==========================================
|
| 105 |
+
# UPLOAD DATA FOLDER
|
| 106 |
+
# ==========================================
|
| 107 |
+
|
| 108 |
+
try:
|
| 109 |
+
|
| 110 |
+
api.upload_folder(
|
| 111 |
+
folder_path=DATA_PATH,
|
| 112 |
+
repo_id=repo_id,
|
| 113 |
+
repo_type=repo_type
|
| 114 |
+
)
|
| 115 |
+
|
| 116 |
+
print(
|
| 117 |
+
"Folder Uploaded Successfully"
|
| 118 |
+
)
|
| 119 |
+
|
| 120 |
+
except Exception as e:
|
| 121 |
+
|
| 122 |
+
print(
|
| 123 |
+
f"Upload Error: {e}"
|
| 124 |
+
)
|
| 125 |
+
raise
|
| 126 |
+
|
| 127 |
+
# ==========================================
|
| 128 |
+
# VERIFY FILES
|
| 129 |
+
# ==========================================
|
| 130 |
+
|
| 131 |
+
try:
|
| 132 |
+
|
| 133 |
+
files = api.list_repo_files(
|
| 134 |
+
repo_id=repo_id,
|
| 135 |
+
repo_type=repo_type
|
| 136 |
+
)
|
| 137 |
+
|
| 138 |
+
print("\nFiles Uploaded:")
|
| 139 |
+
print(files)
|
| 140 |
+
|
| 141 |
+
except Exception as e:
|
| 142 |
+
|
| 143 |
+
print(
|
| 144 |
+
f"Verification Error: {e}"
|
| 145 |
+
)
|
| 146 |
+
raise
|
| 147 |
+
|
| 148 |
+
print("\nDataset Registration Completed Successfully")
|
model_building/model_experiment.py
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
import json
|
| 3 |
+
import joblib
|
| 4 |
+
import pandas as pd
|
| 5 |
+
from datasets import load_dataset
|
| 6 |
+
from sklearn.ensemble import RandomForestClassifier
|
| 7 |
+
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report, confusion_matrix
|
| 8 |
+
from huggingface_hub import HfApi, create_repo
|
| 9 |
+
|
| 10 |
+
# ==========================================
|
| 11 |
+
# 1. ENVIRONMENT SETUP & REPOSITORY CONFIG
|
| 12 |
+
# ==========================================
|
| 13 |
+
TOKEN = os.getenv("HF_TOKEN")
|
| 14 |
+
DATASET_REPO = "vyasmax9/predictive-maintenance-engine"
|
| 15 |
+
MODEL_REPO = "vyasmax9/predictive-maintenance-model"
|
| 16 |
+
api = HfApi(token=TOKEN)
|
| 17 |
+
|
| 18 |
+
MODEL_PATH = os.path.join(os.getcwd(), "Predictive_Maintenance", "models")
|
| 19 |
+
os.makedirs(MODEL_PATH, exist_ok=True)
|
| 20 |
+
|
| 21 |
+
# ==========================================
|
| 22 |
+
# 2. LOAD TRAIN / TEST DATA SPLITS FROM HUB
|
| 23 |
+
# ==========================================
|
| 24 |
+
print("--- Loading train and test CSV files from Hugging Face Hub ---")
|
| 25 |
+
train_df = load_dataset(DATASET_REPO, data_files="train.csv", split="train").to_pandas()
|
| 26 |
+
test_df = load_dataset(DATASET_REPO, data_files="test.csv", split="train").to_pandas()
|
| 27 |
+
|
| 28 |
+
TARGET = "Engine_Condition"
|
| 29 |
+
X_train = train_df.drop(columns=[TARGET])
|
| 30 |
+
y_train = train_df[TARGET]
|
| 31 |
+
X_test = test_df.drop(columns=[TARGET])
|
| 32 |
+
y_test = test_df[TARGET]
|
| 33 |
+
|
| 34 |
+
# ==========================================
|
| 35 |
+
# 3. INITIALIZE CHAMPION WITH BEST PARAMETERS
|
| 36 |
+
# ==========================================
|
| 37 |
+
print("\n--- Training Champion Random Forest Classifier with Optimized Parameters ---")
|
| 38 |
+
|
| 39 |
+
# Replace these key-value pairs with the exact values printed by your Random Forest cell
|
| 40 |
+
best_params = {
|
| 41 |
+
"n_estimators": 200,
|
| 42 |
+
"max_depth": None,
|
| 43 |
+
"min_samples_split": 2,
|
| 44 |
+
"class_weight": "balanced",
|
| 45 |
+
"random_state": 42,
|
| 46 |
+
"n_jobs": -1
|
| 47 |
+
}
|
| 48 |
+
|
| 49 |
+
best_model = RandomForestClassifier(**best_params)
|
| 50 |
+
best_model.fit(X_train, y_train)
|
| 51 |
+
|
| 52 |
+
# ==========================================
|
| 53 |
+
# 4. FINAL PRODUCTION EVALUATION MATRICES
|
| 54 |
+
# ==========================================
|
| 55 |
+
preds = best_model.predict(X_test)
|
| 56 |
+
|
| 57 |
+
final_metrics = {
|
| 58 |
+
"Accuracy": round(accuracy_score(y_test, preds), 4),
|
| 59 |
+
"Precision": round(precision_score(y_test, preds, average='weighted'), 4),
|
| 60 |
+
"Recall": round(recall_score(y_test, preds, average='weighted'), 4),
|
| 61 |
+
"F1-Score": round(f1_score(y_test, preds, average='weighted'), 4)
|
| 62 |
+
}
|
| 63 |
+
|
| 64 |
+
print("\nFinal Optimized Model Metrics:")
|
| 65 |
+
for metric_name, value in final_metrics.items():
|
| 66 |
+
print(f" - {metric_name}: {value}")
|
| 67 |
+
|
| 68 |
+
print("\nClassification Report:")
|
| 69 |
+
print(classification_report(y_test, preds))
|
| 70 |
+
|
| 71 |
+
print("Confusion Matrix Array:")
|
| 72 |
+
print(confusion_matrix(y_test, preds))
|
| 73 |
+
|
| 74 |
+
# ==========================================
|
| 75 |
+
# 5. LOCAL FILE SERIALIZATION
|
| 76 |
+
# ==========================================
|
| 77 |
+
# Export parameters dictionary
|
| 78 |
+
params_path = os.path.join(MODEL_PATH, "best_params.json")
|
| 79 |
+
with open(params_path, "w") as file:
|
| 80 |
+
json.dump(best_params, file, indent=4)
|
| 81 |
+
|
| 82 |
+
# Export evaluation metrics table
|
| 83 |
+
metrics_path = os.path.join(MODEL_PATH, "final_metrics.json")
|
| 84 |
+
with open(metrics_path, "w") as file:
|
| 85 |
+
json.dump(final_metrics, file, indent=4)
|
| 86 |
+
|
| 87 |
+
# Export feature importance scores
|
| 88 |
+
if hasattr(best_model, "feature_importances_"):
|
| 89 |
+
importance_df = pd.DataFrame({
|
| 90 |
+
"Feature": X_train.columns,
|
| 91 |
+
"Importance": best_model.feature_importances_
|
| 92 |
+
}).sort_values(by="Importance", ascending=False)
|
| 93 |
+
|
| 94 |
+
importance_path = os.path.join(MODEL_PATH, "feature_importance.csv")
|
| 95 |
+
importance_df.to_csv(importance_path, index=False)
|
| 96 |
+
|
| 97 |
+
# Save the final binary weight file
|
| 98 |
+
model_file = os.path.join(MODEL_PATH, "best_model.pkl")
|
| 99 |
+
joblib.dump(best_model, model_file)
|
| 100 |
+
print("\n[SUCCESS] Local serialization of production artifacts completed.")
|
| 101 |
+
|
| 102 |
+
# ==========================================
|
| 103 |
+
# 6. REGISTRATION TO HUGGING FACE MODEL HUB
|
| 104 |
+
# ==========================================
|
| 105 |
+
print("\n--- Registering Production Model to Hugging Face Model Hub ---")
|
| 106 |
+
try:
|
| 107 |
+
create_repo(repo_id=MODEL_REPO, repo_type="model", token=TOKEN, private=False, exist_ok=True)
|
| 108 |
+
|
| 109 |
+
upload_list = [model_file, params_path, metrics_path]
|
| 110 |
+
if 'importance_path' in locals():
|
| 111 |
+
upload_list.append(importance_path)
|
| 112 |
+
|
| 113 |
+
for file_to_upload in upload_list:
|
| 114 |
+
api.upload_file(
|
| 115 |
+
path_or_fileobj=file_to_upload,
|
| 116 |
+
path_in_repo=os.path.basename(file_to_upload),
|
| 117 |
+
repo_id=MODEL_REPO,
|
| 118 |
+
repo_type="model"
|
| 119 |
+
)
|
| 120 |
+
print("\n[SUCCESS] Production Model Hub Repository fully synchronized on Hugging Face!")
|
| 121 |
+
except Exception as e:
|
| 122 |
+
print(f"\n[ERROR] Problem encountered during repository file push: {e}")
|
model_building/model_registration.py
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
import mlflow
|
| 3 |
+
|
| 4 |
+
from huggingface_hub import (
|
| 5 |
+
|
| 6 |
+
HfApi,
|
| 7 |
+
|
| 8 |
+
create_repo
|
| 9 |
+
|
| 10 |
+
)
|
| 11 |
+
|
| 12 |
+
from huggingface_hub.utils import (
|
| 13 |
+
|
| 14 |
+
RepositoryNotFoundError
|
| 15 |
+
|
| 16 |
+
)
|
| 17 |
+
|
| 18 |
+
# =====================================
|
| 19 |
+
# Configure MLflow
|
| 20 |
+
# =====================================
|
| 21 |
+
|
| 22 |
+
mlflow.set_tracking_uri(
|
| 23 |
+
"file:./mlruns"
|
| 24 |
+
)
|
| 25 |
+
|
| 26 |
+
mlflow.set_experiment(
|
| 27 |
+
"predictive-maintenance"
|
| 28 |
+
)
|
| 29 |
+
|
| 30 |
+
api = HfApi()
|
| 31 |
+
|
| 32 |
+
# =====================================
|
| 33 |
+
# Paths
|
| 34 |
+
# =====================================
|
| 35 |
+
|
| 36 |
+
MODEL_PATH = "Predictive_Maintenance/models/best_model.pkl"
|
| 37 |
+
|
| 38 |
+
repo_id = "vyasmax9/predictive-maintenance-model"
|
| 39 |
+
|
| 40 |
+
# =====================================
|
| 41 |
+
# Verify Model Exists
|
| 42 |
+
# =====================================
|
| 43 |
+
|
| 44 |
+
if not os.path.exists(
|
| 45 |
+
MODEL_PATH
|
| 46 |
+
):
|
| 47 |
+
|
| 48 |
+
raise FileNotFoundError(
|
| 49 |
+
|
| 50 |
+
f"Model not found: {MODEL_PATH}"
|
| 51 |
+
|
| 52 |
+
)
|
| 53 |
+
|
| 54 |
+
# =====================================
|
| 55 |
+
# Start Tracking
|
| 56 |
+
# =====================================
|
| 57 |
+
|
| 58 |
+
with mlflow.start_run():
|
| 59 |
+
|
| 60 |
+
mlflow.log_param(
|
| 61 |
+
|
| 62 |
+
"model_name",
|
| 63 |
+
|
| 64 |
+
"best_model.pkl"
|
| 65 |
+
|
| 66 |
+
)
|
| 67 |
+
|
| 68 |
+
mlflow.log_artifact(
|
| 69 |
+
|
| 70 |
+
MODEL_PATH,
|
| 71 |
+
|
| 72 |
+
artifact_path="model"
|
| 73 |
+
|
| 74 |
+
)
|
| 75 |
+
|
| 76 |
+
# =====================================
|
| 77 |
+
# Create Repo If Needed
|
| 78 |
+
# =====================================
|
| 79 |
+
|
| 80 |
+
try:
|
| 81 |
+
|
| 82 |
+
api.repo_info(
|
| 83 |
+
|
| 84 |
+
repo_id=repo_id,
|
| 85 |
+
|
| 86 |
+
repo_type="model"
|
| 87 |
+
|
| 88 |
+
)
|
| 89 |
+
|
| 90 |
+
print(
|
| 91 |
+
"Model Repository Exists"
|
| 92 |
+
)
|
| 93 |
+
|
| 94 |
+
except RepositoryNotFoundError:
|
| 95 |
+
|
| 96 |
+
create_repo(
|
| 97 |
+
|
| 98 |
+
repo_id=repo_id,
|
| 99 |
+
|
| 100 |
+
repo_type="model",
|
| 101 |
+
|
| 102 |
+
private=False
|
| 103 |
+
|
| 104 |
+
)
|
| 105 |
+
|
| 106 |
+
print(
|
| 107 |
+
"Created New Model Repository"
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
# =====================================
|
| 111 |
+
# Upload Model
|
| 112 |
+
# =====================================
|
| 113 |
+
|
| 114 |
+
api.upload_file(
|
| 115 |
+
|
| 116 |
+
path_or_fileobj=MODEL_PATH,
|
| 117 |
+
|
| 118 |
+
path_in_repo="best_model.pkl",
|
| 119 |
+
|
| 120 |
+
repo_id=repo_id,
|
| 121 |
+
|
| 122 |
+
repo_type="model"
|
| 123 |
+
|
| 124 |
+
)
|
| 125 |
+
|
| 126 |
+
print(
|
| 127 |
+
"Model Uploaded Successfully"
|
| 128 |
+
)
|
model_building/prep.py
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from huggingface_hub import HfApi
|
| 2 |
+
import os
|
| 3 |
+
import pandas as pd
|
| 4 |
+
from sklearn.model_selection import train_test_split
|
| 5 |
+
|
| 6 |
+
# ==========================================
|
| 7 |
+
# HF TOKEN
|
| 8 |
+
# ==========================================
|
| 9 |
+
|
| 10 |
+
TOKEN = os.getenv("HF_TOKEN")
|
| 11 |
+
|
| 12 |
+
if not TOKEN:
|
| 13 |
+
raise Exception("HF_TOKEN not found")
|
| 14 |
+
|
| 15 |
+
TOKEN = TOKEN.strip()
|
| 16 |
+
|
| 17 |
+
print("HF Token Loaded Successfully")
|
| 18 |
+
|
| 19 |
+
# ==========================================
|
| 20 |
+
# HF API
|
| 21 |
+
# ==========================================
|
| 22 |
+
|
| 23 |
+
api = HfApi()
|
| 24 |
+
|
| 25 |
+
repo_id = "vyasmax9/predictive-maintenance-engine"
|
| 26 |
+
|
| 27 |
+
# ==========================================
|
| 28 |
+
# PATHS
|
| 29 |
+
# ==========================================
|
| 30 |
+
|
| 31 |
+
save_path = os.path.join(
|
| 32 |
+
os.getcwd(),
|
| 33 |
+
"Predictive_Maintenance",
|
| 34 |
+
"data"
|
| 35 |
+
)
|
| 36 |
+
|
| 37 |
+
os.makedirs(
|
| 38 |
+
save_path,
|
| 39 |
+
exist_ok=True
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
dataset_path = os.path.join(
|
| 43 |
+
save_path,
|
| 44 |
+
"engine_data.csv"
|
| 45 |
+
)
|
| 46 |
+
|
| 47 |
+
print("Dataset Path:", dataset_path)
|
| 48 |
+
print("Dataset Exists:", os.path.exists(dataset_path))
|
| 49 |
+
|
| 50 |
+
if not os.path.exists(dataset_path):
|
| 51 |
+
raise FileNotFoundError(
|
| 52 |
+
f"Dataset not found: {dataset_path}"
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
# ==========================================
|
| 56 |
+
# LOAD DATASET
|
| 57 |
+
# ==========================================
|
| 58 |
+
|
| 59 |
+
df = pd.read_csv(dataset_path)
|
| 60 |
+
|
| 61 |
+
print("Dataset Loaded Successfully")
|
| 62 |
+
print("Shape:", df.shape)
|
| 63 |
+
|
| 64 |
+
# ==========================================
|
| 65 |
+
# TRAIN TEST SPLIT
|
| 66 |
+
# ==========================================
|
| 67 |
+
|
| 68 |
+
train_df, test_df = train_test_split(
|
| 69 |
+
df,
|
| 70 |
+
test_size=0.2,
|
| 71 |
+
random_state=42
|
| 72 |
+
)
|
| 73 |
+
|
| 74 |
+
print("Train Shape:", train_df.shape)
|
| 75 |
+
print("Test Shape:", test_df.shape)
|
| 76 |
+
|
| 77 |
+
# ==========================================
|
| 78 |
+
# SAVE FILES
|
| 79 |
+
# ==========================================
|
| 80 |
+
|
| 81 |
+
train_path = os.path.join(
|
| 82 |
+
save_path,
|
| 83 |
+
"train.csv"
|
| 84 |
+
)
|
| 85 |
+
|
| 86 |
+
test_path = os.path.join(
|
| 87 |
+
save_path,
|
| 88 |
+
"test.csv"
|
| 89 |
+
)
|
| 90 |
+
|
| 91 |
+
train_df.to_csv(
|
| 92 |
+
train_path,
|
| 93 |
+
index=False
|
| 94 |
+
)
|
| 95 |
+
|
| 96 |
+
test_df.to_csv(
|
| 97 |
+
test_path,
|
| 98 |
+
index=False
|
| 99 |
+
)
|
| 100 |
+
|
| 101 |
+
print("Train CSV Saved")
|
| 102 |
+
print("Test CSV Saved")
|
| 103 |
+
|
| 104 |
+
# ==========================================
|
| 105 |
+
# UPLOAD TRAIN FILE
|
| 106 |
+
# ==========================================
|
| 107 |
+
|
| 108 |
+
api.upload_file(
|
| 109 |
+
path_or_fileobj=train_path,
|
| 110 |
+
path_in_repo="train.csv",
|
| 111 |
+
repo_id=repo_id,
|
| 112 |
+
repo_type="dataset",
|
| 113 |
+
token=TOKEN
|
| 114 |
+
)
|
| 115 |
+
|
| 116 |
+
print("train.csv uploaded")
|
| 117 |
+
|
| 118 |
+
# ==========================================
|
| 119 |
+
# UPLOAD TEST FILE
|
| 120 |
+
# ==========================================
|
| 121 |
+
|
| 122 |
+
api.upload_file(
|
| 123 |
+
path_or_fileobj=test_path,
|
| 124 |
+
path_in_repo="test.csv",
|
| 125 |
+
repo_id=repo_id,
|
| 126 |
+
repo_type="dataset",
|
| 127 |
+
token=TOKEN
|
| 128 |
+
)
|
| 129 |
+
|
| 130 |
+
print("test.csv uploaded")
|
| 131 |
+
|
| 132 |
+
# ==========================================
|
| 133 |
+
# VERIFY FILES
|
| 134 |
+
# ==========================================
|
| 135 |
+
|
| 136 |
+
files = api.list_repo_files(
|
| 137 |
+
repo_id=repo_id,
|
| 138 |
+
repo_type="dataset",
|
| 139 |
+
token=TOKEN
|
| 140 |
+
)
|
| 141 |
+
|
| 142 |
+
print("\nFiles Uploaded:")
|
| 143 |
+
print(files)
|
| 144 |
+
|
| 145 |
+
print("\nData Preparation Completed")
|
models/best_model.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e140b71071c3ace1d0883330bc4b6896e604a6aa528e7b61718354e3ee3c0ef
|
| 3 |
+
size 100147273
|
models/best_params.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_estimators": 200,
|
| 3 |
+
"max_depth": null,
|
| 4 |
+
"min_samples_split": 2,
|
| 5 |
+
"class_weight": "balanced",
|
| 6 |
+
"random_state": 42,
|
| 7 |
+
"n_jobs": -1
|
| 8 |
+
}
|
models/feature_importance.csv
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Feature,Importance
|
| 2 |
+
Engine_RPM,0.22753045540374342
|
| 3 |
+
Fuel_Pressure,0.16503340519834353
|
| 4 |
+
Lub_Oil_Temperature,0.15893902772340662
|
| 5 |
+
Lub_Oil_Pressure,0.15304628244540297
|
| 6 |
+
Coolant_Temperature,0.14923144007738604
|
| 7 |
+
Coolant_Pressure,0.14621938915171748
|
models/final_metrics.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Accuracy": 0.6496,
|
| 3 |
+
"Precision": 0.6311,
|
| 4 |
+
"Recall": 0.6496,
|
| 5 |
+
"F1-Score": 0.6291
|
| 6 |
+
}
|
models/model_comparison_matrix.csv
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
,Accuracy,Precision,Recall,F1-Score
|
| 2 |
+
Random Forest,0.6496032761709751,0.6688388216128218,0.6496032761709751,0.6549160477054105
|
| 3 |
+
XGBoost,0.6429485538776555,0.6727409853036613,0.6429485538776555,0.6490870197278636
|
| 4 |
+
Gradient Boosting,0.6647043767596621,0.6484145866975868,0.6647043767596621,0.6427105885077777
|
| 5 |
+
AdaBoost,0.6567699001791656,0.6405334577085224,0.6567699001791656,0.6394045447165251
|
models/model_specs.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_algorithm": "Random Forest",
|
| 3 |
+
"f1_score": 0.6549160477054105,
|
| 4 |
+
"accuracy": 0.6496032761709751
|
| 5 |
+
}
|
requirements.txt
CHANGED
|
@@ -7,4 +7,4 @@ mlflow
|
|
| 7 |
huggingface_hub
|
| 8 |
datasets
|
| 9 |
matplotlib
|
| 10 |
-
seaborn
|
|
|
|
| 7 |
huggingface_hub
|
| 8 |
datasets
|
| 9 |
matplotlib
|
| 10 |
+
seaborn
|