Update app.py

app.py

@@ -5,29 +5,37 @@ from scipy.stats import boxcox
 import numpy as np
 import plotly.express as px
 import plotly.graph_objects as go
+import joblib  # For saving and loading models
+import os  # For file directory
+from datetime import datetime
+from stqdm import stqdm
+from ydata_profiling import ProfileReport
+from streamlit_pandas_profiling import st_profile_report
+import shap
+
+# PDF and OCR Processing
+import pdfplumber
+import pytesseract
+from pdf2image import convert_from_path
+
+# Machine Learning
 from sklearn.impute import SimpleImputer
-from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import GridSearchCV, cross_val_score, train_test_split
 from sklearn.linear_model import LogisticRegression
 from sklearn.svm import SVC
-from sklearn.ensemble import GradientBoostingRegressor, GradientBoostingClassifier
+from sklearn.ensemble import GradientBoostingRegressor, GradientBoostingClassifier, RandomForestClassifier, RandomForestRegressor
 from sklearn.neural_network import MLPRegressor, MLPClassifier
-from sklearn.metrics import confusion_matrix, classification_report, r2_score
-from sklearn.model_selection import cross_val_score
-import scipy.stats as stats
-import matplotlib.pyplot as plt #For SHAP charts
-from scipy.stats import pearsonr, spearmanr
+from sklearn.metrics import confusion_matrix, classification_report, r2_score, accuracy_score, mean_squared_error
 from sklearn.inspection import permutation_importance
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.preprocessing import StandardScaler, LabelEncoder
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
-from sklearn.metrics import accuracy_score, mean_squared_error
-from ydata_profiling import ProfileReport
-from streamlit_pandas_profiling import st_profile_report
-import joblib  # For saving and loading models
-import os  # For file directory
-# Advanced
-from transformers import TFBertForSequenceClassification
+
+# Visualization
+import matplotlib.pyplot as plt # For SHAP charts
+import scipy.stats as stats
+from scipy.stats import pearsonr, spearmanr
+
+# Advanced and Neural Network Models
 import tensorflow as tf
 from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense, Conv2D, LSTM, Embedding, Dropout, Flatten, MaxPooling2D, BatchNormalization
@@ -36,14 +44,30 @@ from tensorflow.keras.utils import plot_model
 from tensorflow.keras.callbacks import Callback
 import tf2onnx
 import onnx
-import shap
-from datetime import datetime
-from stqdm import stqdm
+
+# Transformers and BERT
+from transformers import TFBertForSequenceClassification
+
 
 
 # --------------------------
 # Helper Functions
 # --------------------------
+pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'  # Update this path if Tesseract is installed elsewhere
+
+def extract_text_from_pdf(pdf_path, ocr_enabled=False):
+    text = ""
+    if ocr_enabled:
+        images = convert_from_path(pdf_path)
+        for image in images:
+            text += pytesseract.image_to_string(image)
+    else:
+        with pdfplumber.open(pdf_path) as pdf:
+            for page in pdf.pages:
+                text += page.extract_text()
+    return text
+
+
 def enhance_section_title(title, icon="✨"):
     """Helper function to create a styled section title with an icon."""
     st.markdown(f"<h2 style='border-bottom: 2px solid #ccc; padding-bottom: 5px;'>{icon} {title}</h2>", unsafe_allow_html=True)
@@ -1632,11 +1656,9 @@ elif app_mode == "Predictions":
             st.error(f"Prediction failed: {str(e)}")
 
 
-
 elif app_mode == "PDF Analysis":
     st.title("📄 Advanced PDF Analyzer")
-    
-    # PDF Upload with drag & drop zone
+# PDF Upload with drag & drop zone
     with st.container(border=True):
         uploaded_pdfs = st.file_uploader("Drag & Drop PDF Files", 
                                        type="pdf",