workbench 0.8.168__py3-none-any.whl → 0.8.192__py3-none-any.whl

workbench/model_scripts/quant_regression/quant_regression.template

@@ -1,279 +0,0 @@
-# Imports for XGB Model
-import xgboost as xgb
-import awswrangler as wr
-from sklearn.model_selection import train_test_split
-
-# Model Performance Scores
-from sklearn.metrics import (
-    mean_absolute_error,
-    r2_score,
-    root_mean_squared_error
-)
-
-from io import StringIO
-import json
-import argparse
-import os
-import pandas as pd
-
-# Template Placeholders
-TEMPLATE_PARAMS = {
-    "model_type": "{{model_type}}",
-    "target_column": "{{target_column}}",
-    "features": "{{feature_list}}",
-    "model_metrics_s3_path": "{{model_metrics_s3_path}}",
-    "train_all_data": "{{train_all_data}}"
-}
-
-# Function to check if dataframe is empty
-def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
-    """
-    Check if the provided dataframe is empty and raise an exception if it is.
-
-    Args:
-        df (pd.DataFrame): DataFrame to check
-        df_name (str): Name of the DataFrame
-    """
-    if df.empty:
-        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
-        print(msg)
-        raise ValueError(msg)
-
-
-def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
-    """
-    Matches and renames DataFrame columns to match model feature names (case-insensitive).
-    Prioritizes exact matches, then case-insensitive matches.
-
-    Raises ValueError if any model features cannot be matched.
-    """
-    df_columns_lower = {col.lower(): col for col in df.columns}
-    rename_dict = {}
-    missing = []
-    for feature in model_features:
-        if feature in df.columns:
-            continue  # Exact match
-        elif feature.lower() in df_columns_lower:
-            rename_dict[df_columns_lower[feature.lower()]] = feature
-        else:
-            missing.append(feature)
-
-    if missing:
-        raise ValueError(f"Features not found: {missing}")
-
-    # Rename the DataFrame columns to match the model features
-    return df.rename(columns=rename_dict)
-
-if __name__ == "__main__":
-    """The main function is for training the XGBoost Quantile Regression models"""
-
-    # Harness Template Parameters
-    target = TEMPLATE_PARAMS["target_column"]
-    features = TEMPLATE_PARAMS["features"]
-    model_metrics_s3_path = TEMPLATE_PARAMS["model_metrics_s3_path"]
-    train_all_data = TEMPLATE_PARAMS["train_all_data"]
-    validation_split = 0.2
-    quantiles = [0.025, 0.25, 0.50, 0.75, 0.975]
-    q_models = {}
-
-    # Script arguments for input/output directories
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--model-dir", type=str, default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
-    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
-    parser.add_argument(
-        "--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR", "/opt/ml/output/data")
-    )
-    args = parser.parse_args()
-
-    # Load training data from the specified directory
-    training_files = [
-        os.path.join(args.train, file)
-        for file in os.listdir(args.train) if file.endswith(".csv")
-    ]
-    print(f"Training Files: {training_files}")
-
-    # Combine files and read them all into a single pandas dataframe
-    df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
-
-    # Check if the DataFrame is empty
-    check_dataframe(df, "training_df")
-
-    # Training data split logic
-    if train_all_data:
-        # Use all data for both training and validation
-        print("Training on all data...")
-        df_train = df.copy()
-        df_val = df.copy()
-    elif "training" in df.columns:
-        # Split data based on a 'training' column if it exists
-        print("Splitting data based on 'training' column...")
-        df_train = df[df["training"]].copy()
-        df_val = df[~df["training"]].copy()
-    else:
-        # Perform a random split if no 'training' column is found
-        print("Splitting data randomly...")
-        df_train, df_val = train_test_split(df, test_size=validation_split, random_state=42)
-
-    # Features/Target output
-    print(f"Target: {target}")
-    print(f"Features: {str(features)}")
-    print(f"Data Shape: {df.shape}")
-
-    # Prepare features and targets for training
-    X_train = df_train[features]
-    X_val = df_val[features]
-    y_train = df_train[target]
-    y_val = df_val[target]
-
-    # Train models for each of the quantiles
-    for q in quantiles:
-        params = {
-            "objective": "reg:quantileerror",
-            "quantile_alpha": q,
-        }
-        model = xgb.XGBRegressor(**params)
-        model.fit(X_train, y_train)
-
-        # Convert quantile to string
-        q_str = f"q_{int(q * 100)}" if (q * 100) == int(q * 100) else f"q_{int(q * 1000):03d}"
-
-        # Store the model
-        q_models[q_str] = model
-
-    # Run predictions for each quantile
-    quantile_predictions = {q: model.predict(X_val) for q, model in q_models.items()}
-
-    # Create a copy of the validation DataFrame and add the new columns
-    result_df = df_val[[target]].copy()
-
-    # Add the quantile predictions to the DataFrame
-    for name, preds in quantile_predictions.items():
-        result_df[name] = preds
-
-    # Add the median as the main prediction
-    result_df["prediction"] = result_df["q_50"]
-
-    # Now compute residuals on the prediction
-    result_df["residual"] = result_df[target] - result_df["prediction"]
-    result_df["residual_abs"] = result_df["residual"].abs()
-
-    # Save the results dataframe to S3
-    wr.s3.to_csv(
-        result_df,
-        path=f"{model_metrics_s3_path}/validation_predictions.csv",
-        index=False,
-    )
-
-    # Report Performance Metrics
-    rmse = root_mean_squared_error(result_df[target], result_df["prediction"])
-    mae = mean_absolute_error(result_df[target], result_df["prediction"])
-    r2 = r2_score(result_df[target], result_df["prediction"])
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(result_df)}")
-
-    # Now save the quantile models
-    for name, model in q_models.items():
-        model_path = os.path.join(args.model_dir, f"{name}.json")
-        print(f"Saving model:  {model_path}")
-        model.save_model(model_path)
-
-    # Also save the features (this will validate input during predictions)
-    with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
-        json.dump(features, fp)
-
-
-def model_fn(model_dir) -> dict:
-    """Deserialized and return all the fitted models from the model directory.
-
-    Args:
-        model_dir (str): The directory where the models are stored.
-
-    Returns:
-        dict: A dictionary of the models.
-    """
-
-    # Load ALL the Quantile models from the model directory
-    models = {}
-    for file in os.listdir(model_dir):
-        if file.startswith("q") and file.endswith(".json"):  # The Quantile models
-            # Load the model
-            model_path = os.path.join(model_dir, file)
-            print(f"Loading model: {model_path}")
-            model = xgb.XGBRegressor()
-            model.load_model(model_path)
-
-            # Store the quantile model
-            q_name = os.path.splitext(file)[0]
-            models[q_name] = model
-
-    # Return all the models
-    return models
-
-
-def input_fn(input_data, content_type):
-    """Parse input data and return a DataFrame."""
-    if not input_data:
-        raise ValueError("Empty input data is not supported!")
-
-    # Decode bytes to string if necessary
-    if isinstance(input_data, bytes):
-        input_data = input_data.decode("utf-8")
-
-    if "text/csv" in content_type:
-        return pd.read_csv(StringIO(input_data))
-    elif "application/json" in content_type:
-        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
-    else:
-        raise ValueError(f"{content_type} not supported!")
-
-
-def output_fn(output_df, accept_type):
-    """Supports both CSV and JSON output formats."""
-    if "text/csv" in accept_type:
-        csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
-        return csv_output, "text/csv"
-    elif "application/json" in accept_type:
-        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
-    else:
-        raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
-
-
-def predict_fn(df, models) -> pd.DataFrame:
-    """Make Predictions with our XGB Quantile Regression Model
-
-    Args:
-        df (pd.DataFrame): The input DataFrame
-        models (dict): The dictionary of models to use for predictions
-
-    Returns:
-        pd.DataFrame: The DataFrame with the predictions added
-    """
-
-    # Grab our feature columns (from training)
-    model_dir = os.environ.get("SM_MODEL_DIR", "/opt/ml/model")
-    with open(os.path.join(model_dir, "feature_columns.json")) as fp:
-        model_features = json.load(fp)
-    print(f"Model Features: {model_features}")
-
-    # We're going match features in a case-insensitive manner, accounting for all the permutations
-    # - Model has a feature list that's any case ("Id", "taCos", "cOunT", "likes_tacos")
-    # - Incoming data has columns that are mixed case ("ID", "Tacos", "Count", "Likes_Tacos")
-    matched_df = match_features_case_insensitive(df, model_features)
-
-    # Predict the features against all the models
-    for name, model in models.items():
-        df[name] = model.predict(matched_df[model_features])
-
-    # Use the median prediction as the main prediction
-    df["prediction"] = df["q_50"]
-
-    # Estimate the standard deviation of the predictions using the interquartile range
-    df["prediction_std"] = (df["q_75"] - df["q_25"]) / 1.35
-
-    # Reorganize the columns so they are in alphabetical order
-    df = df.reindex(sorted(df.columns), axis=1)
-
-    # All done, return the DataFrame
-    return df

workbench/model_scripts/quant_regression/requirements.txt

@@ -1 +0,0 @@
-# Note: In general this file should be empty (as the default inference image has all required libraries)

workbench/model_scripts/scikit_learn/generated_model_script.py

@@ -1,307 +0,0 @@
-# Model Imports (this will be replaced with the imports for the template)
-None
-
-# Template Placeholders
-TEMPLATE_PARAMS = {
-    "model_type": "regressor",
-    "target_column": "solubility",
-    "feature_list": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct'],
-    "model_class": PyTorch,
-    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-pytorch-reg/training",
-    "train_all_data": False
-}
-
-import awswrangler as wr
-from sklearn.preprocessing import LabelEncoder, StandardScaler
-from sklearn.model_selection import train_test_split
-from sklearn.pipeline import Pipeline
-
-from io import StringIO
-import json
-import argparse
-import joblib
-import os
-import pandas as pd
-from typing import List
-
-# Global model_type for both training and inference
-model_type = TEMPLATE_PARAMS["model_type"]
-
-
-# Function to check if dataframe is empty
-def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
-    """Check if the DataFrame is empty and raise an error if so."""
-    if df.empty:
-        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
-        print(msg)
-        raise ValueError(msg)
-
-
-# Function to expand probability column into individual class probability columns
-def expand_proba_column(df: pd.DataFrame, class_labels: List[str]) -> pd.DataFrame:
-    """Expand 'pred_proba' column into separate columns for each class label."""
-    proba_column = "pred_proba"
-    if proba_column not in df.columns:
-        raise ValueError('DataFrame does not contain a "pred_proba" column')
-
-    # Create new columns for each class label's probability
-    new_col_names = [f"{label}_proba" for label in class_labels]
-    proba_df = pd.DataFrame(df[proba_column].tolist(), columns=new_col_names)
-
-    # Drop the original 'pred_proba' column and reset the index
-    df = df.drop(columns=[proba_column]).reset_index(drop=True)
-
-    # Concatenate the new probability columns with the original DataFrame
-    df = pd.concat([df, proba_df], axis=1)
-    return df
-
-
-# Function to match DataFrame columns to model features (case-insensitive)
-def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
-    """Match and rename DataFrame columns to match the model's features, case-insensitively."""
-    # Create a set of exact matches from the DataFrame columns
-    exact_match_set = set(df.columns)
-
-    # Create a case-insensitive map of DataFrame columns
-    column_map = {col.lower(): col for col in df.columns}
-    rename_dict = {}
-
-    # Build a dictionary for renaming columns based on case-insensitive matching
-    for feature in model_features:
-        if feature in exact_match_set:
-            rename_dict[feature] = feature
-        elif feature.lower() in column_map:
-            rename_dict[column_map[feature.lower()]] = feature
-
-    # Rename columns in the DataFrame to match model features
-    return df.rename(columns=rename_dict)
-
-
-#
-# Training Section
-#
-if __name__ == "__main__":
-    # Template Parameters
-    target = TEMPLATE_PARAMS["target_column"]  # Can be None for unsupervised models
-    feature_list = TEMPLATE_PARAMS["feature_list"]
-    model_class = TEMPLATE_PARAMS["model_class"]
-    model_metrics_s3_path = TEMPLATE_PARAMS["model_metrics_s3_path"]
-    train_all_data = TEMPLATE_PARAMS["train_all_data"]
-    validation_split = 0.2
-
-    # Script arguments for input/output directories
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--model-dir", type=str, default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
-    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
-    parser.add_argument(
-        "--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR", "/opt/ml/output/data")
-    )
-    args = parser.parse_args()
-
-    # Load training data from the specified directory
-    training_files = [
-        os.path.join(args.train, file)
-        for file in os.listdir(args.train) if file.endswith(".csv")
-    ]
-    all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
-
-    # Check if the DataFrame is empty
-    check_dataframe(all_df, "training_df")
-
-    # Initialize the model using the specified model class
-    model = model_class()
-
-    # Determine if standardization is needed based on the model type
-    needs_standardization = model_type in ["clusterer", "projection"]
-
-    if needs_standardization:
-        # Create a pipeline with standardization and the model
-        model = Pipeline([
-            ("scaler", StandardScaler()),
-            ("model", model)
-        ])
-
-    # Handle logic based on the model_type
-    if model_type in ["classifier", "regressor"]:
-        # Supervised Models: Prepare for training
-        if train_all_data:
-            # Use all data for both training and validation
-            print("Training on all data...")
-            df_train = all_df.copy()
-            df_val = all_df.copy()
-        elif "training" in all_df.columns:
-            # Split data based on a 'training' column if it exists
-            print("Splitting data based on 'training' column...")
-            df_train = all_df[all_df["training"]].copy()
-            df_val = all_df[~all_df["training"]].copy()
-        else:
-            # Perform a random split if no 'training' column is found
-            print("Splitting data randomly...")
-            df_train, df_val = train_test_split(all_df, test_size=validation_split, random_state=42)
-
-        # Encode the target variable if the model is a classifier
-        label_encoder = None
-        if model_type == "classifier" and target:
-            label_encoder = LabelEncoder()
-            df_train[target] = label_encoder.fit_transform(df_train[target])
-            df_val[target] = label_encoder.transform(df_val[target])
-
-        # Prepare features and targets for training
-        X_train = df_train[feature_list]
-        X_val = df_val[feature_list]
-        y_train = df_train[target] if target else None
-        y_val = df_val[target] if target else None
-
-        # Train the model using the training data
-        model.fit(X_train, y_train)
-
-        # Make predictions and handle classification-specific logic
-        preds = model.predict(X_val)
-        if model_type == "classifier" and target:
-            # Get class probabilities and expand them into separate columns
-            probs = model.predict_proba(X_val)
-            df_val["pred_proba"] = [p.tolist() for p in probs]
-            df_val = expand_proba_column(df_val, label_encoder.classes_)
-
-            # Decode the target and prediction labels
-            df_val[target] = label_encoder.inverse_transform(df_val[target])
-            preds = label_encoder.inverse_transform(preds)
-
-        # Add predictions to the validation DataFrame
-        df_val["prediction"] = preds
-
-        # Save the validation predictions to S3
-        output_columns = [target, "prediction"] + [col for col in df_val.columns if col.endswith("_proba")]
-        wr.s3.to_csv(df_val[output_columns], path=f"{model_metrics_s3_path}/validation_predictions.csv", index=False)
-
-    elif model_type == "clusterer":
-        # Unsupervised Clustering Models: Assign cluster labels
-        all_df["cluster"] = model.fit_predict(all_df[feature_list])
-
-    elif model_type == "projection":
-        # Projection Models: Apply transformation and label first three components as x, y, z
-        transformed_data = model.fit_transform(all_df[feature_list])
-        num_components = transformed_data.shape[1]
-
-        # Special labels for the first three components, if they exist
-        special_labels = ["x", "y", "z"]
-        for i in range(num_components):
-            if i < len(special_labels):
-                all_df[special_labels[i]] = transformed_data[:, i]
-            else:
-                all_df[f"component_{i + 1}"] = transformed_data[:, i]
-
-    elif model_type == "transformer":
-        # Transformer Models: Apply transformation and use generic component labels
-        transformed_data = model.fit_transform(all_df[feature_list])
-        for i in range(transformed_data.shape[1]):
-            all_df[f"component_{i + 1}"] = transformed_data[:, i]
-
-    # Save the trained model and any necessary assets
-    joblib.dump(model, os.path.join(args.model_dir, "model.joblib"))
-    if model_type == "classifier" and label_encoder:
-        joblib.dump(label_encoder, os.path.join(args.model_dir, "label_encoder.joblib"))
-
-    # Save the feature list to validate input during predictions
-    with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
-        json.dump(feature_list, fp)
-
-#
-# Inference Section
-#
-def model_fn(model_dir):
-    """Load and return the model from the specified directory."""
-    return joblib.load(os.path.join(model_dir, "model.joblib"))
-
-
-def input_fn(input_data, content_type):
-    """Parse input data and return a DataFrame."""
-    if not input_data:
-        raise ValueError("Empty input data is not supported!")
-
-    # Decode bytes to string if necessary
-    if isinstance(input_data, bytes):
-        input_data = input_data.decode("utf-8")
-
-    if "text/csv" in content_type:
-        return pd.read_csv(StringIO(input_data))
-    elif "application/json" in content_type:
-        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
-    else:
-        raise ValueError(f"{content_type} not supported!")
-
-
-def output_fn(output_df, accept_type):
-    """Supports both CSV and JSON output formats."""
-    if "text/csv" in accept_type:
-        csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
-        return csv_output, "text/csv"
-    elif "application/json" in accept_type:
-        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
-    else:
-        raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
-
-
-def predict_fn(df, model):
-    """Make predictions or apply transformations using the model and return the DataFrame with results."""
-    model_dir = os.environ.get("SM_MODEL_DIR", "/opt/ml/model")
-
-    # Load feature columns from the saved file
-    with open(os.path.join(model_dir, "feature_columns.json")) as fp:
-        model_features = json.load(fp)
-
-    # Load label encoder if available (for classification models)
-    label_encoder = None
-    if os.path.exists(os.path.join(model_dir, "label_encoder.joblib")):
-        label_encoder = joblib.load(os.path.join(model_dir, "label_encoder.joblib"))
-
-    # Match features in a case-insensitive manner
-    matched_df = match_features_case_insensitive(df, model_features)
-
-    # Initialize a dictionary to store the results
-    results = {}
-
-    # Determine how to handle the model based on its available methods
-    if hasattr(model, "predict"):
-        # For supervised models (classifier or regressor)
-        predictions = model.predict(matched_df[model_features])
-        results["prediction"] = predictions
-
-    elif hasattr(model, "fit_predict"):
-        # For clustering models (e.g., DBSCAN)
-        clusters = model.fit_predict(matched_df[model_features])
-        results["cluster"] = clusters
-
-    elif hasattr(model, "fit_transform") and not hasattr(model, "predict"):
-        # For transformation/projection models (e.g., t-SNE, PCA)
-        transformed_data = model.fit_transform(matched_df[model_features])
-
-        # Handle 2D projection models specifically
-        if model_type == "projection" and transformed_data.shape[1] == 2:
-            results["x"] = transformed_data[:, 0]
-            results["y"] = transformed_data[:, 1]
-        else:
-            # General case for any number of components
-            for i in range(transformed_data.shape[1]):
-                results[f"component_{i + 1}"] = transformed_data[:, i]
-
-    else:
-        # Raise an error if the model does not support the expected methods
-        raise ValueError("Model does not support predict, fit_predict, or fit_transform methods.")
-
-    # Decode predictions if using a label encoder (for classification)
-    if label_encoder and "prediction" in results:
-        results["prediction"] = label_encoder.inverse_transform(results["prediction"])
-
-    # Add the results to the DataFrame
-    for key, value in results.items():
-        df[key] = value
-
-    # Add probability columns if the model supports it (for classification)
-    if hasattr(model, "predict_proba"):
-        probs = model.predict_proba(matched_df[model_features])
-        df["pred_proba"] = [p.tolist() for p in probs]
-        df = expand_proba_column(df, label_encoder.classes_)
-
-    # Return the modified DataFrame
-    return df