avatar2102 commited on
Commit
27b28e6
·
verified ·
1 Parent(s): 98fc88f

Upload final AdaBoost model and experiment log

Browse files
adaboost_final_model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199bac0eaec7724fd9ee921ed80cba8f7f0e5f7ba9a5e07a59e5051bb85d64df
3
+ size 97796
data_register.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from huggingface_hub import HfApi
2
+ from huggingface_hub.utils import RepositoryNotFoundError, HfHubHTTPError
3
+ import os
4
+
5
+ repo_id = "avatar2102/engine-predictive-maintenance"
6
+ repo_type = "dataset"
7
+
8
+ token = os.getenv("PREDICTIVE_GIT_TOKEN")
9
+ if token is None:
10
+ raise ValueError("PREDICTIVE_GIT_TOKEN environment variable not set")
11
+
12
+ api = HfApi(token=token)
13
+
14
+ try:
15
+ api.repo_info(repo_id=repo_id, repo_type=repo_type)
16
+ print(f"Dataset repo '{repo_id}' already exists. Using it.")
17
+ except (RepositoryNotFoundError, HfHubHTTPError):
18
+ print(f"Dataset repo '{repo_id}' not found. Creating new repo...")
19
+ api.create_repo(repo_id=repo_id, repo_type=repo_type, exist_ok=True)
20
+ print(f"Dataset repo '{repo_id}' created.")
21
+
22
+ api.upload_folder(
23
+ folder_path="prediction_project/data",
24
+ repo_id=repo_id,
25
+ repo_type=repo_type,
26
+ commit_message="Add engine predictive maintenance dataset"
27
+ )
28
+
29
+ print("Dataset uploaded successfully.")
final_adaboost_model_log.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ model,n_estimators,learning_rate,cv_f1_score,test_accuracy,test_precision,test_recall,test_f1_score,confusion_matrix
2
+ AdaBoost,150,0.05,0.7742989393943112,0.6539544407473765,0.6536652835408022,0.9593991067803491,0.7775584073708457,"[[192, 1252], [100, 2363]]"
prep.py ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from huggingface_hub import HfApi
2
+ from sklearn.model_selection import train_test_split
3
+ import pandas as pd
4
+ import os
5
+
6
+ repo_id = "avatar2102/engine-predictive-maintenance"
7
+ token = os.getenv("PREDICTIVE_GIT_TOKEN")
8
+
9
+ if token is None:
10
+ raise ValueError("PREDICTIVE_GIT_TOKEN environment variable not set")
11
+
12
+ api = HfApi(token=token)
13
+
14
+ # Load dataset directly from Hugging Face using pandas
15
+ data_path = f"hf://datasets/{repo_id}/engine_data.csv"
16
+ df = pd.read_csv(data_path)
17
+
18
+ print("Dataset loaded successfully from Hugging Face.")
19
+ print("Original shape:", df.shape)
20
+
21
+ # Standardize column names
22
+ df.columns = df.columns.str.strip().str.lower().str.replace(" ", "_")
23
+
24
+ # Basic cleaning
25
+ df = df.drop_duplicates()
26
+ df = df.dropna()
27
+
28
+ print("Data cleaning completed.")
29
+ print("Shape after cleaning:", df.shape)
30
+
31
+ # Split into train and test
32
+ train_df, test_df = train_test_split(
33
+ df,
34
+ test_size=0.2,
35
+ random_state=42,
36
+ stratify=df["engine_condition"]
37
+ )
38
+
39
+ # Save locally
40
+ train_df.to_csv("prediction_project/data/train.csv", index=False)
41
+ test_df.to_csv("prediction_project/data/test.csv", index=False)
42
+
43
+ print("Train and test datasets saved locally.")
44
+
45
+ # Upload updated data folder back to Hugging Face
46
+ api.upload_folder(
47
+ folder_path="prediction_project/data",
48
+ repo_id=repo_id,
49
+ repo_type="dataset",
50
+ commit_message="Upload processed train and test datasets"
51
+ )
52
+
53
+ print("Train and test datasets uploaded successfully to Hugging Face.")
train.py ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ import pandas as pd
3
+ import joblib
4
+
5
+ from sklearn.ensemble import AdaBoostClassifier
6
+ from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix
7
+ from huggingface_hub import HfApi
8
+ from huggingface_hub.utils import RepositoryNotFoundError, HfHubHTTPError
9
+
10
+ DATASET_REPO_ID = "avatar2102/engine-predictive-maintenance"
11
+ MODEL_REPO_ID = "avatar2102/engine-predictive-maintenance-model"
12
+
13
+ token = os.getenv("PREDICTIVE_GIT_TOKEN")
14
+ if token is None:
15
+ raise ValueError("PREDICTIVE_GIT_TOKEN environment variable not set")
16
+
17
+ api = HfApi(token=token)
18
+
19
+ # Load train/test data from Hugging Face dataset repo
20
+ train_path = f"hf://datasets/{DATASET_REPO_ID}/train.csv"
21
+ test_path = f"hf://datasets/{DATASET_REPO_ID}/test.csv"
22
+
23
+ train_df = pd.read_csv(train_path)
24
+ test_df = pd.read_csv(test_path)
25
+
26
+ print("Train and test datasets loaded successfully from Hugging Face.")
27
+ print("Train shape:", train_df.shape)
28
+ print("Test shape:", test_df.shape)
29
+
30
+ # Split features and target
31
+ X_train = train_df.drop("engine_condition", axis=1)
32
+ y_train = train_df["engine_condition"]
33
+
34
+ X_test = test_df.drop("engine_condition", axis=1)
35
+ y_test = test_df["engine_condition"]
36
+
37
+ print("Feature-target split completed.")
38
+
39
+ # Final AdaBoost model using tuned parameters from interim phase
40
+ final_model = AdaBoostClassifier(
41
+ n_estimators=150,
42
+ learning_rate=0.05,
43
+ random_state=42
44
+ )
45
+
46
+ # Train model
47
+ final_model.fit(X_train, y_train)
48
+ print("Final AdaBoost model trained successfully.")
49
+
50
+ # Predict on test data
51
+ y_pred = final_model.predict(X_test)
52
+
53
+ # Evaluate model
54
+ accuracy = accuracy_score(y_test, y_pred)
55
+ precision = precision_score(y_test, y_pred)
56
+ recall = recall_score(y_test, y_pred)
57
+ f1 = f1_score(y_test, y_pred)
58
+ cm = confusion_matrix(y_test, y_pred)
59
+
60
+ print("Model evaluation completed.")
61
+ print("Accuracy:", accuracy)
62
+ print("Precision:", precision)
63
+ print("Recall:", recall)
64
+ print("F1-score:", f1)
65
+ print("Confusion Matrix:")
66
+ print(cm)
67
+
68
+ # Save experiment log
69
+ log_df = pd.DataFrame([{
70
+ "model": "AdaBoost",
71
+ "n_estimators": 150,
72
+ "learning_rate": 0.05,
73
+ "cv_f1_score": 0.7742989393943112,
74
+ "test_accuracy": accuracy,
75
+ "test_precision": precision,
76
+ "test_recall": recall,
77
+ "test_f1_score": f1,
78
+ "confusion_matrix": str(cm.tolist())
79
+ }])
80
+
81
+ log_df.to_csv("prediction_project/model_building/final_adaboost_model_log.csv", index=False)
82
+ print("Experiment log saved successfully.")
83
+
84
+ # Save model locally
85
+ joblib.dump(final_model, "prediction_project/model_building/adaboost_final_model.joblib")
86
+ print("Model saved locally as joblib.")
87
+
88
+ # Create model repo if missing
89
+ try:
90
+ api.repo_info(repo_id=MODEL_REPO_ID, repo_type="model")
91
+ print(f"Model repo '{MODEL_REPO_ID}' already exists. Using it.")
92
+ except (RepositoryNotFoundError, HfHubHTTPError):
93
+ print(f"Model repo '{MODEL_REPO_ID}' not found. Creating new repo...")
94
+ api.create_repo(repo_id=MODEL_REPO_ID, repo_type="model", exist_ok=True)
95
+ print(f"Model repo '{MODEL_REPO_ID}' created.")
96
+
97
+ # Upload model_building folder to HF Model Hub
98
+ api.upload_folder(
99
+ folder_path="prediction_project/model_building",
100
+ repo_id=MODEL_REPO_ID,
101
+ repo_type="model",
102
+ commit_message="Upload final AdaBoost model and experiment log"
103
+ )
104
+
105
+ print("Model uploaded successfully to Hugging Face Model Hub.")