Initial commit of AutoML project

.env

@@ -0,0 +1 @@
+# GROQ_API_KEY="YOUR_GROQ_API_KEY_HERE"

app.py

@@ -18,6 +18,7 @@ import re
 import matplotlib.pyplot as plt
 import io
 import base64
+import numpy as np
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -71,6 +72,7 @@ def get_learning_type():
         logging.warning("No dataset uploaded when requesting learning type.")
         return jsonify({"error": "No dataset uploaded yet."}), 400
 
+    dtypes_str = df.dtypes.to_string()
     prompt = (
         "You are an expert data scientist. Your task is to analyze a dataset and determine its learning type (supervised or unsupervised). "
         "If it's a supervised learning problem, you MUST identify the single target column that the other columns would predict. "

frontend/main.js

@@ -42,10 +42,10 @@ document.addEventListener('DOMContentLoaded', () => {
     });
 
     function formatAIResponse(text) {
-        text = text.replace(/\*\*(.*?)\*\*/g, '<strong>$1</strong>');
-        text = text.replace(/^\d+\.\s+(.*)/gm, '<li>$1</li>');
+        text = text.replace(/\*\*(.*?)\*\*/g, '<strong>$1<\/strong>');
+        text = text.replace(/^\d+\.\s+(.*)/gm, '<li>$1<\/li>');
         text = text.replace(/(<li>.*<\/li>)/s, '<ol>$1<\/ol>');
-        text = text.replace(/^\*\s+(.*)/gm, '<li>$1</li>');
+        text = text.replace(/^\*\s+(.*)/gm, '<li>$1<\/li>');
         text = text.replace(/(<li>.*<\/li>)/s, '<ul>$1<\/ul>');
         return text;
     }
@@ -167,7 +167,14 @@ document.addEventListener('DOMContentLoaded', () => {
     function formatMetrics(metrics) {
         let formatted = '\n';
         for (const [key, value] of Object.entries(metrics)) {
-            formatted += `<strong>${key}:</strong> ${JSON.stringify(value, null, 2)}\n`;
+            if (typeof value === 'object' && value !== null) {
+                formatted += `<strong>${key}:<\/strong>\n`;
+                for (const [subKey, subValue] of Object.entries(value)) {
+                    formatted += `  ${subKey}: ${subValue}\n`;
+                }
+            } else {
+                formatted += `<strong>${key}:<\/strong> ${value}\n`;
+            }
         }
         return formatted;
     }
@@ -234,13 +241,11 @@ document.addEventListener('DOMContentLoaded', () => {
                 output += formatMetrics(result.metrics);
             }
             if (result.result) {
-                output += `\n<strong>Result:</strong> ${JSON.stringify(result.result, null, 2)}`;
+                output += `\n<strong>Result:<\/strong> ${JSON.stringify(result.result, null, 2)}`;
             }
             trainOutput.innerHTML = output;
         } catch (error) {
             trainOutput.textContent = `Error: ${error.message}`;
-        } finally {
-            loader.style.display = 'none';
         }
     });
 
@@ -295,4 +300,4 @@ document.addEventListener('DOMContentLoaded', () => {
             });
         });
     });
-});
+});

groq_config.json

@@ -0,0 +1 @@
+{"GROQ_API_KEY": "YOUR_GROQ_API_KEY_HERE"}

models/xgboost_model.py

@@ -1,37 +0,0 @@
-import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import LabelEncoder
-from xgboost import XGBClassifier, XGBRegressor
-from utils.metrics import classification_metrics, regression_metrics
-
-def encode_dataframe(df):
-    label_encoders = {}
-    for col in df.select_dtypes(include='object'):
-        le = LabelEncoder()
-        df[col] = le.fit_transform(df[col])
-        label_encoders[col] = le
-    return df, label_encoders
-
-def train_xgboost(df, target_column, task='classification'):
-    df = df.dropna()
-    df, encoders = encode_dataframe(df)
-
-    X = df.drop(columns=[target_column])
-    y = df[target_column]
-
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
-
-    if task == 'classification':
-        model = XGBClassifier()
-    else:
-        model = XGBRegressor()
-
-    model.fit(X_train, y_train)
-    y_pred = model.predict(X_test)
-
-    if task == 'classification':
-        metrics = classification_metrics(y_test, y_pred)
-    else:
-        metrics = regression_metrics(y_test, y_pred)
-
-    return model, metrics

requirements.txt

@@ -6,10 +6,7 @@ seaborn
 plotly
 xgboost
 catboost
-langgraph
 python-dotenv
-faiss-cpu
-tiktoken
 groq
 flask
 scipy

utils/export.py

@@ -1,12 +0,0 @@
-import pickle
-import os
-
-def save_model(model, path='model.pkl'):
-    with open(path, 'wb') as f:
-        pickle.dump(model, f)
-
-def load_model(path='model.pkl'):
-    if os.path.exists(path):
-        with open(path, 'rb') as f:
-            return pickle.load(f)
-    return None