Upload train.py

train.py

@@ -0,0 +1,117 @@
+import skops
+import sklearn
+import matplotlib.pyplot as plt
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.compose import ColumnTransformer
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.pipeline import Pipeline
+
+# preprocess the dataset
+
+df = pd.read_csv("../input/tabular-playground-series-aug-2022/train.csv")
+
+
+column_transformer_pipeline = ColumnTransformer([
+                ("loading_missing_value_imputer", SimpleImputer(strategy="mean"), ["loading"]),
+                ("numerical_missing_value_imputer", SimpleImputer(strategy="mean"), list(df.columns[df.dtypes == 'float64'])),
+                ("attribute_0_encoder", OneHotEncoder(categories = "auto"), ["attribute_0"]),
+                ("attribute_1_encoder", OneHotEncoder(categories = "auto"), ["attribute_1"]),
+                ("product_code_encoder", OneHotEncoder(categories = "auto"), ["product_code"])])
+
+df = df.drop(["id"], axis=1)
+
+
+pipeline = Pipeline([
+    ('transformation', column_transformer_pipeline),
+    ('model', DecisionTreeClassifier(max_depth=4))
+])
+
+X = df.drop(["failure"], axis = 1)
+y = df.failure
+
+# split the data and train the model 
+
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y)
+pipeline.fit(X_train, y_train)
+
+# we will now use skops to initialize a repository
+# create a model card, and push the model to the 
+# Hugging Face Hub
+from skops import card, hub_utils
+import pickle
+
+model_path = "model.pkl"
+local_repo = "decision-tree-playground-kaggle"
+
+# save the model
+with open(model_path, mode="bw") as f:
+    pickle.dump(pipeline, file=f)
+
+# initialize the repository
+hub_utils.init(
+model=model_path, 
+requirements=[f"scikit-learn={sklearn.__version__}"], 
+dst=local_repo,
+task="tabular-classification",
+data=X_test,
+)
+
+# initialize the model card
+from pathlib import Path
+model_card = card.Card(pipeline, metadata=card.metadata_from_config(Path(local_repo)))
+
+## let's fill some information about the model
+limitations = "This model is not ready to be used in production."
+model_description = "This is a DecisionTreeClassifier model built for Kaggle Tabular Playground Series August 2022, trained on supersoaker production failures dataset."
+model_card_authors = "huggingface"
+get_started_code = f"import pickle \nwith open({local_repo}/{model_path}, 'rb') as file: \n    clf = pickle.load(file)"
+
+# pass this information to the card
+model_card.add(
+    get_started_code=get_started_code,
+    model_card_authors=model_card_authors,
+    limitations=limitations,
+    model_description=model_description,
+)
+
+# we will now evaluate the model and write eval results to the card
+from sklearn.metrics import accuracy_score, f1_score, ConfusionMatrixDisplay, confusion_matrix
+model_card.add(eval_method="The model is evaluated using test split, on accuracy and F1 score with micro average.")
+model_card.add_metrics(accuracy=accuracy_score(y_test, y_pred))
+model_card.add_metrics(**{"f1 score": f1_score(y_test, y_pred, average="micro")})
+
+model = pipeline.steps[-1][1]
+
+# we will plot the tree and add the plot to our card
+from sklearn.tree import plot_tree
+plt.figure()
+plot_tree(model,filled=True)  
+plt.savefig(f'{local_repo}/tree.png',format='png',bbox_inches = "tight")
+
+# let's make a prediction and evaluate the model
+y_pred = pipeline.predict(X_test)
+cm = confusion_matrix(y_test, y_pred, labels=model.classes_)
+disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=model.classes_)
+disp.plot()
+
+# save the plot
+plt.savefig(Path(local_repo) / "confusion_matrix.png")
+
+# add figures to model card with their new sections as keys to the dictionary
+model_card.add_plot(**{"Tree Plot": f'{local_repo}/tree.png', "Confusion Matrix": f"{local_repo}/confusion_matrix.png"})
+
+#save the card
+model_card.save(f"{local_repo}/README.md")
+
+# we can now push the model!
+# if the repository doesn't exist remotely on the Hugging Face Hub, it will be created when we set create_remote to True
+repo_id = "scikit-learn/tabular-playground"
+hub_utils.push(
+    repo_id=repo_id,
+    source=local_repo,
+    token=token,
+    commit_message="pushing files to the repo from the example!",
+    create_remote=True,
+)