app.py

from transformers import Tool
import pandas as pd
import numpy as np
import plotly.express as px
import seaborn as sns
from sklearn import preprocessing, decomposition, metrics

# 1. Data Loading and Preprocessing Tool
class DataPreprocessingTool(Tool):
    name = "data_preprocessor"
    description = "Handles data loading, cleaning, and preprocessing tasks"

    inputs = {
        "data": {"type": "dict", "description": "Input data dictionary"},
        "operation": {"type": "string", "description": "Operation to perform: clean/encode/normalize/impute"}
    }
    output_type = "dict"

    def forward(self, data: dict, operation: str) -> dict:
        df = pd.DataFrame(data)
        if operation == "clean":
            # Handle duplicates, missing values
            df = df.drop_duplicates()
            df = df.fillna(df.mean(numeric_only=True))
        elif operation == "encode":
            # Encode categorical variables
            le = preprocessing.LabelEncoder()
            for col in df.select_dtypes(include=['object']):
                df[col] = le.fit_transform(df[col].astype(str))
        elif operation == "normalize":
            # Normalize numeric columns
            scaler = preprocessing.StandardScaler()
            numeric_cols = df.select_dtypes(include=[np.number]).columns
            df[numeric_cols] = scaler.fit_transform(df[numeric_cols])
        return df.to_dict()

# 2. Statistical Analysis Tool
class StatisticalAnalysisTool(Tool):
    name = "statistical_analyzer"
    description = "Performs statistical analysis on data"

    inputs = {
        "data": {"type": "dict", "description": "Input data dictionary"},
        "analysis_type": {"type": "string", "description": "Type of analysis: descriptive/inferential/correlation"}
    }
    output_type = "dict"

    def forward(self, data: dict, analysis_type: str) -> dict:
        df = pd.DataFrame(data)
        if analysis_type == "descriptive":
            return {
                "summary": df.describe().to_dict(),
                "skewness": df.skew().to_dict(),
                "kurtosis": df.kurtosis().to_dict()
            }
        elif analysis_type == "inferential":
            # Perform statistical tests
            results = {}
            numeric_cols = df.select_dtypes(include=[np.number]).columns
            for col in numeric_cols:
                from scipy import stats
                stat, p_value = stats.normaltest(df[col].dropna())
                results[col] = {"statistic": stat, "p_value": p_value}
            return results
        return df.corr().to_dict()

# 3. Advanced Visualization Tool
class AdvancedVisualizationTool(Tool):
    name = "advanced_visualizer"
    description = "Creates advanced statistical and ML visualizations"

    inputs = {
        "data": {"type": "dict", "description": "Input data dictionary"},
        "viz_type": {"type": "string", "description": "Type of visualization"},
        "params": {"type": "dict", "description": "Additional parameters"}
    }
    output_type = "dict"

    def forward(self, data: dict, viz_type: str, params: dict) -> dict:
        df = pd.DataFrame(data)
        if viz_type == "pca":
            # PCA visualization
            pca = decomposition.PCA(n_components=2)
            numeric_cols = df.select_dtypes(include=[np.number]).columns
            pca_result = pca.fit_transform(df[numeric_cols])
            fig = px.scatter(x=pca_result[:, 0], y=pca_result[:, 1], 
                           title='PCA Visualization')
            return {"plot": fig.to_dict()}
        elif viz_type == "cluster":
            # Clustering visualization
            from sklearn.cluster import KMeans
            kmeans = KMeans(n_clusters=params.get("n_clusters", 3))
            numeric_cols = df.select_dtypes(include=[np.number]).columns
            clusters = kmeans.fit_predict(df[numeric_cols])
            fig = px.scatter(df, x=params.get("x"), y=params.get("y"), 
                           color=clusters, title='Cluster Visualization')
            return {"plot": fig.to_dict()}
        return {}

# 4. Machine Learning Tool
class MLModelTool(Tool):
    name = "ml_modeler"
    description = "Trains and evaluates machine learning models"

    inputs = {
        "data": {"type": "dict", "description": "Input data dictionary"},
        "target": {"type": "string", "description": "Target column name"},
        "model_type": {"type": "string", "description": "Type of model to train"}
    }
    output_type = "dict"

    def forward(self, data: dict, target: str, model_type: str) -> dict:
        from sklearn.model_selection import train_test_split
        from sklearn.metrics import mean_squared_error, accuracy_score
        
        df = pd.DataFrame(data)
        X = df.drop(columns=[target])
        y = df[target]
        
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
        
        if model_type == "regression":
            from sklearn.linear_model import LinearRegression
            model = LinearRegression()
            model.fit(X_train, y_train)
            y_pred = model.predict(X_test)
            return {
                "mse": mean_squared_error(y_test, y_pred),
                "r2": model.score(X_test, y_test),
                "coefficients": dict(zip(X.columns, model.coef_))
            }
        elif model_type == "classification":
            from sklearn.ensemble import RandomForestClassifier
            model = RandomForestClassifier()
            model.fit(X_train, y_train)
            y_pred = model.predict(X_test)
            return {
                "accuracy": accuracy_score(y_test, y_pred),
                "feature_importance": dict(zip(X.columns, model.feature_importances_))
            }
        return {}