Offline Travel Expense Splitter App

import tkinter as tk

from tkinter import ttk, messagebox

import sqlite3

from fpdf import FPDF


# ---------------------------------------------------

# DATABASE SETUP

# ---------------------------------------------------

conn = sqlite3.connect("travel_expenses.db")

cursor = conn.cursor()


cursor.execute("""

CREATE TABLE IF NOT EXISTS members (

    id INTEGER PRIMARY KEY AUTOINCREMENT,

    name TEXT NOT NULL

)

""")


cursor.execute("""

CREATE TABLE IF NOT EXISTS expenses (

    id INTEGER PRIMARY KEY AUTOINCREMENT,

    member_id INTEGER,

    description TEXT,

    amount REAL,

    FOREIGN KEY(member_id) REFERENCES members(id)

)

""")


conn.commit()


# ---------------------------------------------------

# MAIN APPLICATION

# ---------------------------------------------------

class TravelExpenseApp:


    def __init__(self, root):

        self.root = root

        self.root.title("Travel Expense Splitter")

        self.root.geometry("600x500")


        self.create_ui()


    # ------------------------ UI ------------------------

    def create_ui(self):

        tab_control = ttk.Notebook(self.root)


        self.tab_members = ttk.Frame(tab_control)

        self.tab_expenses = ttk.Frame(tab_control)

        self.tab_summary = ttk.Frame(tab_control)


        tab_control.add(self.tab_members, text="Members")

        tab_control.add(self.tab_expenses, text="Expenses")

        tab_control.add(self.tab_summary, text="Summary")

        tab_control.pack(expand=1, fill="both")


        self.setup_members_tab()

        self.setup_expenses_tab()

        self.setup_summary_tab()


    # ------------------------ MEMBERS TAB ------------------------

    def setup_members_tab(self):

        tk.Label(self.tab_members, text="Add Member", font=("Arial", 14)).pack(pady=10)


        self.member_entry = tk.Entry(self.tab_members, font=("Arial", 12))

        self.member_entry.pack(pady=5)


        tk.Button(self.tab_members, text="Add Member", command=self.add_member).pack(pady=10)


        self.members_list = tk.Listbox(self.tab_members, width=40, height=10)

        self.members_list.pack(pady=10)


        self.load_members()


    def add_member(self):

        name = self.member_entry.get()

        if not name:

            messagebox.showerror("Error", "Please enter a name!")

            return


        cursor.execute("INSERT INTO members (name) VALUES (?)", (name,))

        conn.commit()

        self.member_entry.delete(0, tk.END)

        self.load_members()


    def load_members(self):

        self.members_list.delete(0, tk.END)

        cursor.execute("SELECT name FROM members")

        for row in cursor.fetchall():

            self.members_list.insert(tk.END, row[0])


    # ------------------------ EXPENSE TAB ------------------------

    def setup_expenses_tab(self):

        tk.Label(self.tab_expenses, text="Add Expense", font=("Arial", 14)).pack(pady=10)


        tk.Label(self.tab_expenses, text="Select Member:").pack()

        self.member_dropdown = ttk.Combobox(self.tab_expenses, state="readonly")

        self.member_dropdown.pack(pady=5)


        self.load_member_dropdown()


        tk.Label(self.tab_expenses, text="Description:").pack()

        self.desc_entry = tk.Entry(self.tab_expenses, font=("Arial", 12))

        self.desc_entry.pack(pady=5)


        tk.Label(self.tab_expenses, text="Amount:").pack()

        self.amount_entry = tk.Entry(self.tab_expenses, font=("Arial", 12))

        self.amount_entry.pack(pady=5)


        tk.Button(self.tab_expenses, text="Add Expense", command=self.add_expense).pack(pady=10)


        self.expense_tree = ttk.Treeview(self.tab_expenses, columns=("member", "desc", "amount"), show="headings")

        self.expense_tree.heading("member", text="Member")

        self.expense_tree.heading("desc", text="Description")

        self.expense_tree.heading("amount", text="Amount")

        self.expense_tree.pack(fill="both", expand=True)


        self.load_expenses()


    def load_member_dropdown(self):

        cursor.execute("SELECT name FROM members")

        members = [row[0] for row in cursor.fetchall()]

        self.member_dropdown["values"] = members


    def add_expense(self):

        member = self.member_dropdown.get()

        desc = self.desc_entry.get()

        amount = self.amount_entry.get()


        if not member or not desc or not amount:

            messagebox.showerror("Error", "All fields are required!")

            return


        try:

            amount = float(amount)

        except:

            messagebox.showerror("Error", "Amount must be a number!")

            return


        cursor.execute("SELECT id FROM members WHERE name=?", (member,))

        member_id = cursor.fetchone()[0]


        cursor.execute("INSERT INTO expenses (member_id, description, amount) VALUES (?, ?, ?)",

                       (member_id, desc, amount))

        conn.commit()


        self.desc_entry.delete(0, tk.END)

        self.amount_entry.delete(0, tk.END)


        self.load_expenses()


    def load_expenses(self):

        for i in self.expense_tree.get_children():

            self.expense_tree.delete(i)


        cursor.execute("""

            SELECT members.name, expenses.description, expenses.amount

            FROM expenses

            JOIN members ON expenses.member_id = members.id

        """)


        for row in cursor.fetchall():

            self.expense_tree.insert("", tk.END, values=row)


    # ------------------------ SUMMARY TAB ------------------------

    def setup_summary_tab(self):

        tk.Label(self.tab_summary, text="Expense Summary", font=("Arial", 14)).pack(pady=10)


        tk.Button(self.tab_summary, text="Calculate Summary", command=self.calculate_summary).pack(pady=10)

        tk.Button(self.tab_summary, text="Export PDF", command=self.export_pdf).pack(pady=10)


        self.summary_box = tk.Text(self.tab_summary, height=20, width=70)

        self.summary_box.pack()


    def calculate_summary(self):

        cursor.execute("SELECT COUNT(*) FROM members")

        num_members = cursor.fetchone()[0]


        cursor.execute("SELECT SUM(amount) FROM expenses")

        total_expense = cursor.fetchone()[0] or 0


        split_amount = total_expense / num_members if num_members > 0 else 0


        self.summary_box.delete(1.0, tk.END)

        self.summary_box.insert(tk.END, f"Total Expense: ₹{total_expense:.2f}\n")

        self.summary_box.insert(tk.END, f"Each Person Should Pay: ₹{split_amount:.2f}\n\n")


        cursor.execute("""

            SELECT members.name, SUM(expenses.amount)

            FROM members

            LEFT JOIN expenses ON members.id = expenses.member_id

            GROUP BY members.name

        """)


        for name, paid in cursor.fetchall():

            paid = paid or 0

            diff = paid - split_amount

            status = "owes" if diff < 0 else "gets back"

            self.summary_box.insert(tk.END, f"{name}: Paid ₹{paid:.2f} → {status} ₹{abs(diff):.2f}\n")


    # ------------------------ PDF EXPORT ------------------------

    def export_pdf(self):

        pdf = FPDF()

        pdf.add_page()

        pdf.set_font("Arial", size=12)


        pdf.cell(200, 10, "Travel Expense Summary", ln=True, align="C")

        pdf.ln(10)


        summary_text = self.summary_box.get(1.0, tk.END).split("\n")

        for line in summary_text:

            pdf.cell(0, 10, txt=line, ln=True)


        pdf.output("Travel_Expense_Summary.pdf")

        messagebox.showinfo("Success", "PDF Exported Successfully!")


# ------------------------ RUN APP ------------------------

root = tk.Tk()

app = TravelExpenseApp(root)

root.mainloop()


AI-Focused Book Summarizer & Chapter Highlighter

import fitz  # PyMuPDF

import nltk

import re

from transformers import pipeline


# Load HuggingFace summarizer

summarizer = pipeline(

    "summarization", 

    model="facebook/bart-large-cnn"

)


# ----------------------------------------

# 1. Extract text from PDF

# ----------------------------------------

def extract_pdf_text(pdf_path):

    doc = fitz.open(pdf_path)

    full_text = ""


    for page in doc:

        full_text += page.get_text()


    return full_text



# ----------------------------------------

# 2. Split text into chapters

#    Uses patterns like:

#     - Chapter 1

#     - CHAPTER I

#     - CHAPTER ONE

# ----------------------------------------

def split_into_chapters(text):

    chapter_pattern = r"(chapter\s+\d+|chapter\s+[ivxlcdm]+|chapter\s+\w+)"

    found = re.split(chapter_pattern, text, flags=re.IGNORECASE)


    chapters = []

    for i in range(1, len(found), 2):

        title = found[i].strip()

        content = found[i + 1].strip()

        chapters.append((title, content))


    # If no chapters are detected → return full book as one chapter

    if not chapters:

        return [("Full Book", text)]


    return chapters



# ----------------------------------------

# 3. Summarize long text in safe chunks

# ----------------------------------------

def summarize_long_text(text, max_chunk=1500):

    nltk.download("punkt", quiet=True)


    sentences = nltk.sent_tokenize(text)

    chunks = []

    current_chunk = ""


    for sentence in sentences:

        if len(current_chunk) + len(sentence) <= max_chunk:

            current_chunk += " " + sentence

        else:

            chunks.append(current_chunk)

            current_chunk = sentence


    if current_chunk:

        chunks.append(current_chunk)


    # Summarize each chunk

    summaries = []

    for chunk in chunks:

        summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)[0]["summary_text"]

        summaries.append(summary)


    # Join all summaries

    return "\n".join(summaries)



# ----------------------------------------

# 4. Generate key points

# ----------------------------------------

def generate_key_points(summary):

    sentences = nltk.sent_tokenize(summary)

    key_points = sentences[:5]   # Top 5 key ideas

    return ["• " + s for s in key_points]



# ----------------------------------------

# 5. End-to-End Pipeline

# ----------------------------------------

def summarize_book(pdf_path):

    print("\nšŸ“˜ Extracting PDF text...")

    text = extract_pdf_text(pdf_path)


    print("✂ Splitting into chapters...")

    chapters = split_into_chapters(text)


    results = []


    for idx, (title, content) in enumerate(chapters, start=1):

        print(f"\nšŸ“ Summarizing {title}...")


        summary = summarize_long_text(content)

        key_points = generate_key_points(summary)


        results.append({

            "chapter_title": title,

            "summary": summary,

            "key_points": key_points

        })


    return results



# ----------------------------------------

# 6. Print Results Nicely

# ----------------------------------------

def display_results(results):

    print("\n============================")

    print("šŸ“š BOOK SUMMARY REPORT")

    print("============================\n")


    for item in results:

        print(f"\n===== {item['chapter_title']} =====\n")

        print("SUMMARY:\n")

        print(item["summary"])


        print("\nKEY POINTS:")

        for p in item["key_points"]:

            print(p)


        print("\n---------------------------")



# ----------------------------------------

# RUN

# ----------------------------------------

if __name__ == "__main__":

    pdf_path = input("Enter PDF file path: ").strip()


    results = summarize_book(pdf_path)

    display_results(results)


    print("\n✔ Done! All chapters processed.")


Backup Scheduler

import schedule

import shutil

import time

import os

from datetime import datetime


# ------------------------------

# CONFIGURATION

# ------------------------------

SOURCE_FOLDER = r"E:\MyData"           # Folder to back up

DESTINATION_FOLDER = r"F:\Backups"     # External drive / backup location


BACKUP_FREQUENCY = "hourly"            # options: hourly, daily, custom



# ------------------------------

# Create destination folder if missing

# ------------------------------

def ensure_destination():

    if not os.path.exists(DESTINATION_FOLDER):

        os.makedirs(DESTINATION_FOLDER)

        print(f"[INFO] Created backup directory: {DESTINATION_FOLDER}")



# ------------------------------

# Perform Backup

# ------------------------------

def perform_backup():

    ensure_destination()


    timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")

    backup_path = os.path.join(DESTINATION_FOLDER, f"backup_{timestamp}")


    try:

        print(f"[START] Backing up '{SOURCE_FOLDER}' → '{backup_path}'")

        shutil.copytree(SOURCE_FOLDER, backup_path)

        print(f"[DONE] Backup completed successfully! ✔️\n")

    except Exception as e:

        print(f"[ERROR] Backup failed: {e}\n")



# ------------------------------

# Schedule Backup

# ------------------------------

def schedule_backups():

    if BACKUP_FREQUENCY == "hourly":

        schedule.every().hour.do(perform_backup)

        print("[SCHEDULER] Backup scheduled: Every hour.")

    

    elif BACKUP_FREQUENCY == "daily":

        schedule.every().day.at("00:00").do(perform_backup)

        print("[SCHEDULER] Backup scheduled: Every day at 12:00 AM.")

    

    else:

        # custom frequency example: every 10 minutes

        schedule.every(10).minutes.do(perform_backup)

        print("[SCHEDULER] Backup scheduled: Every 10 minutes (custom).")



# ------------------------------

# MAIN LOOP

# ------------------------------

def main():

    print("===== Python Backup Scheduler Started =====")

    print(f"Source Folder:      {SOURCE_FOLDER}")

    print(f"Destination Folder: {DESTINATION_FOLDER}")

    print("=================================================\n")


    schedule_backups()


    # Continuous loop

    while True:

        schedule.run_pending()

        time.sleep(1)



if __name__ == "__main__":

    main()


Offline Dictionary App

import tkinter as tk

from tkinter import messagebox

import sqlite3

import pyttsx3


# -----------------------------

# Database Setup

# -----------------------------

def init_db():

    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()


    cur.execute("""

        CREATE TABLE IF NOT EXISTS words (

            word TEXT PRIMARY KEY,

            meaning TEXT

        );

    """)


    cur.execute("""

        CREATE TABLE IF NOT EXISTS favorites (

            word TEXT PRIMARY KEY

        );

    """)


    conn.commit()

    conn.close()


# -----------------------------

# Insert sample words (optional)

# -----------------------------

def insert_sample_words():

    sample_data = {

        "python": "A high-level programming language used for general-purpose programming.",

        "algorithm": "A step-by-step procedure for solving a problem or performing a task.",

        "variable": "A storage location paired with a name used to store values.",

        "database": "A structured collection of data stored electronically.",

    }


    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()

    

    for word, meaning in sample_data.items():

        cur.execute("INSERT OR IGNORE INTO words VALUES (?, ?)", (word, meaning))


    conn.commit()

    conn.close()


# -----------------------------

# Text-to-Speech

# -----------------------------

engine = pyttsx3.init()


def speak_word(word):

    engine.say(word)

    engine.runAndWait()


# -----------------------------

# Dictionary Operations

# -----------------------------

def search_word():

    word = entry_word.get().strip().lower()

    if not word:

        messagebox.showerror("Error", "Please enter a word to search.")

        return


    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()


    cur.execute("SELECT meaning FROM words WHERE word=?", (word,))

    result = cur.fetchone()


    if result:

        text_meaning.config(state="normal")

        text_meaning.delete(1.0, tk.END)

        text_meaning.insert(tk.END, result[0])

        text_meaning.config(state="disabled")

    else:

        messagebox.showinfo("Not Found", "Word not found in offline dictionary.")

    

    conn.close()


def add_word():

    word = entry_add_word.get().strip().lower()

    meaning = text_add_meaning.get(1.0, tk.END).strip()


    if not word or not meaning:

        messagebox.showerror("Error", "Both word and meaning are required.")

        return


    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()


    cur.execute("INSERT OR REPLACE INTO words VALUES (?, ?)", (word, meaning))

    conn.commit()

    conn.close()


    messagebox.showinfo("Success", f"'{word}' added to dictionary.")


def add_to_favorites():

    word = entry_word.get().strip().lower()


    if not word:

        messagebox.showerror("Error", "Search a word first before adding to favorites.")

        return


    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()

    cur.execute("INSERT OR IGNORE INTO favorites VALUES (?)", (word,))

    conn.commit()

    conn.close()


    messagebox.showinfo("Added", f"'{word}' added to favorites!")


def show_favorites():

    conn = sqlite3.connect("dictionary.db")

    cur = conn.cursor()

    cur.execute("SELECT word FROM favorites")

    favs = cur.fetchall()

    conn.close()


    fav_list = "\n".join([w[0] for w in favs]) if favs else "No favorites added yet."


    messagebox.showinfo("Favorite Words", fav_list)


# -----------------------------

# GUI Setup

# -----------------------------

root = tk.Tk()

root.title("Offline Dictionary App")

root.geometry("650x500")

root.resizable(False, False)


# Search section

tk.Label(root, text="Enter Word:", font=("Arial", 14)).pack(pady=5)

entry_word = tk.Entry(root, font=("Arial", 14), width=30)

entry_word.pack()


btn_search = tk.Button(root, text="Search", font=("Arial", 12), command=search_word)

btn_search.pack(pady=5)


btn_speak = tk.Button(root, text="šŸ”Š Speak", font=("Arial", 12), command=lambda: speak_word(entry_word.get()))

btn_speak.pack(pady=2)


btn_fav = tk.Button(root, text="⭐ Add to Favorites", font=("Arial", 12), command=add_to_favorites)

btn_fav.pack(pady=2)


# Meaning display

tk.Label(root, text="Meaning:", font=("Arial", 14)).pack()

text_meaning = tk.Text(root, height=6, width=60, font=("Arial", 12), state="disabled")

text_meaning.pack(pady=5)


# Add new word section

tk.Label(root, text="Add New Word:", font=("Arial", 14)).pack(pady=5)

entry_add_word = tk.Entry(root, font=("Arial", 12), width=30)

entry_add_word.pack()


tk.Label(root, text="Meaning:", font=("Arial", 14)).pack()

text_add_meaning = tk.Text(root, height=4, width=60, font=("Arial", 12))

text_add_meaning.pack()


btn_add = tk.Button(root, text="Add Word to Dictionary", font=("Arial", 12), command=add_word)

btn_add.pack(pady=5)


# favorites

btn_show_fav = tk.Button(root, text="šŸ“Œ Show Favorites", font=("Arial", 12), command=show_favorites)

btn_show_fav.pack(pady=5)


# Run

init_db()

insert_sample_words()

root.mainloop()


Resume ATS Scoring Tool

import fitz  # PyMuPDF

import spacy

import re

import pandas as pd


nlp = spacy.load("en_core_web_sm")


# ---------------------------------------

# Utility: Extract text from PDF or TXT

# ---------------------------------------

def extract_text(file_path):

    if file_path.lower().endswith(".pdf"):

        text = ""

        pdf = fitz.open(file_path)

        for page in pdf:

            text += page.get_text()

        return text

    else:

        # for .txt files

        with open(file_path, "r", encoding="utf-8") as f:

            return f.read()


# ---------------------------------------

# Clean & Normalize Text

# ---------------------------------------

def clean_text(text):

    text = text.lower()

    text = re.sub(r'[^a-zA-Z0-9\s]', ' ', text)

    text = re.sub(r'\s+', ' ', text)

    return text


# ---------------------------------------

# Extract Keywords Using spaCy

# ---------------------------------------

def extract_keywords(text):

    doc = nlp(text)

    keywords = []


    for token in doc:

        # Keep nouns, verbs, adjectives (important for ATS)

        if token.pos_ in ["NOUN", "PROPN", "VERB", "ADJ"]:

            if len(token.text) > 2:

                keywords.append(token.lemma_.lower())


    return list(set(keywords))


# ---------------------------------------

# ATS Scoring Logic

# ---------------------------------------

def calculate_ats_score(resume_text, jd_text):

    resume_clean = clean_text(resume_text)

    jd_clean = clean_text(jd_text)


    resume_keywords = extract_keywords(resume_clean)

    jd_keywords = extract_keywords(jd_clean)


    matched = [kw for kw in jd_keywords if kw in resume_keywords]

    missing = [kw for kw in jd_keywords if kw not in resume_keywords]


    score = (len(matched) / len(jd_keywords)) * 100 if jd_keywords else 0


    return {

        "ats_score": round(score, 2),

        "matched_keywords": matched,

        "missing_keywords": missing,

        "total_keywords": len(jd_keywords)

    }


# ---------------------------------------

# MAIN FUNCTION

# ---------------------------------------

def ats_tool(resume_file, jobdesc_file):

    resume_text = extract_text(resume_file)

    jd_text = extract_text(jobdesc_file)


    result = calculate_ats_score(resume_text, jd_text)


    print("\n ATS SCORING RESULTS")

    print("--------------------------------")

    print(f"ATS Score: {result['ats_score']}%")

    print(f"Total Keywords in Job Description: {result['total_keywords']}")

    print(f"Matched Keywords ({len(result['matched_keywords'])}):")

    print(result["matched_keywords"])

    print("\nMissing Keywords:")

    print(result["missing_keywords"])


    # Export to CSV (optional)

    df = pd.DataFrame({

        "Matched Keywords": pd.Series(result["matched_keywords"]),

        "Missing Keywords": pd.Series(result["missing_keywords"])

    })

    df.to_csv("ats_report.csv", index=False)

    print("\n Report saved as ats_report.csv")


# ---------------------------------------

# RUN

# ---------------------------------------

if __name__ == "__main__":

    resume_path = input("Enter Resume File Path (.pdf/.txt): ")

    jd_path = input("Enter Job Description File Path (.pdf/.txt): ")


    ats_tool(resume_path, jd_path)


Command Palette Launcher (VS Code Style)

 """

Command Palette Launcher (VS Code style)

Tech: tkinter, os, keyboard, difflib


Features:

- Ctrl+P to open palette (global using 'keyboard', and also inside Tk window)

- Index files from a folder for quick search

- Fuzzy search using difflib

- Open files (os.startfile on Windows / xdg-open on Linux / open on macOS)

- Add custom commands (open app, shell command)

- Demo includes uploaded file path: /mnt/data/image.png

"""


import os

import sys

import threading

import platform

import subprocess

from pathlib import Path

import tkinter as tk

from tkinter import ttk, filedialog, messagebox

from difflib import get_close_matches


# Optional global hotkey package

try:

    import keyboard  # pip install keyboard

    KEYBOARD_AVAILABLE = True

except Exception:

    KEYBOARD_AVAILABLE = False


# Demo uploaded file path (from your session)

DEMO_FILE = "/mnt/data/image.png"


# ------------------------------

# Utility functions

# ------------------------------

def open_path(path):

    """Open a file or folder using the OS default application."""

    p = str(path)

    if platform.system() == "Windows":

        os.startfile(p)

    elif platform.system() == "Darwin":  # macOS

        subprocess.Popen(["open", p])

    else:  # Linux and others

        subprocess.Popen(["xdg-open", p])


def is_executable_file(path):

    try:

        return os.access(path, os.X_OK) and Path(path).is_file()

    except Exception:

        return False


# ------------------------------

# Indexer

# ------------------------------

class FileIndexer:

    def __init__(self):

        self.items = []  # list of {"title": ..., "path": ..., "type": "file"|"cmd"}

        # preload demo item if exists

        if Path(DEMO_FILE).exists():

            self.add_item(title=Path(DEMO_FILE).name, path=str(DEMO_FILE), typ="file")


    def add_item(self, title, path, typ="file"):

        rec = {"title": title, "path": path, "type": typ}

        self.items.append(rec)


    def index_folder(self, folder, max_files=5000):

        """Recursively index a folder (stop at max_files)."""

        folder = Path(folder)

        count = 0

        for root, dirs, files in os.walk(folder):

            for f in files:

                try:

                    fp = Path(root) / f

                    self.add_item(title=f, path=str(fp), typ="file")

                    count += 1

                    if count >= max_files:

                        return count

                except Exception:

                    continue

        return count


    def add_common_apps(self):

        """Add some common app commands (platform-specific)."""

        sysplat = platform.system()

        apps = []

        if sysplat == "Windows":

            # common Windows apps (paths may vary)

            apps = [

                ("Notepad", "notepad.exe"),

                ("Calculator", "calc.exe"),

                ("Paint", "mspaint.exe"),

            ]

        elif sysplat == "Darwin":

            apps = [

                ("TextEdit", "open -a TextEdit"),

                ("Calculator", "open -a Calculator"),

            ]

        else:  # Linux

            apps = [

                ("Gedit", "gedit"),

                ("Calculator", "gnome-calculator"),

            ]

        for name, cmd in apps:

            self.add_item(title=name, path=cmd, typ="cmd")


    def search(self, query, limit=15):

        """Simple fuzzy search: look for substrings first, then difflib matches."""

        q = query.strip().lower()

        if not q:

            # return top items

            return self.items[:limit]


        # substring matches (higher priority)

        substr_matches = [it for it in self.items if q in it["title"].lower() or q in it["path"].lower()]

        if len(substr_matches) >= limit:

            return substr_matches[:limit]


        # prepare list of titles for difflib

        titles = [it["title"] for it in self.items]

        close = get_close_matches(q, titles, n=limit, cutoff=0.4)

        # map back to records preserving order (titles may repeat)

        close_records = []

        for t in close:

            for it in self.items:

                if it["title"] == t and it not in close_records:

                    close_records.append(it)

                    break


        # combine substring + close matches, ensure uniqueness

        results = []

        seen = set()

        for it in substr_matches + close_records:

            key = (it["title"], it["path"])

            if key not in seen:

                results.append(it)

                seen.add(key)

            if len(results) >= limit:

                break

        return results


# ------------------------------

# GUI

# ------------------------------

class CommandPalette(tk.Toplevel):

    def __init__(self, master, indexer: FileIndexer):

        super().__init__(master)

        self.indexer = indexer

        self.title("Command Palette")

        self.geometry("700x380")

        self.transient(master)

        self.grab_set()  # modal

        self.resizable(False, False)


        # Styling

        self.configure(bg="#2b2b2b")


        # Search box

        self.search_var = tk.StringVar()

        search_entry = ttk.Entry(self, textvariable=self.search_var, font=("Consolas", 14), width=60)

        search_entry.pack(padx=12, pady=(12,6))

        search_entry.focus_set()

        search_entry.bind("<KeyRelease>", self.on_search_key)

        search_entry.bind("<Escape>", lambda e: self.close())

        search_entry.bind("<Return>", lambda e: self.open_selected())


        # Results list

        self.tree = ttk.Treeview(self, columns=("title","path","type"), show="headings", height=12)

        self.tree.heading("title", text="Title")

        self.tree.heading("path", text="Path / Command")

        self.tree.heading("type", text="Type")

        self.tree.column("title", width=250)

        self.tree.column("path", width=350)

        self.tree.column("type", width=80, anchor="center")

        self.tree.pack(padx=12, pady=6, fill="both", expand=True)

        self.tree.bind("<Double-1>", lambda e: self.open_selected())

        self.tree.bind("<Return>", lambda e: self.open_selected())


        # Bottom buttons

        btn_frame = ttk.Frame(self)

        btn_frame.pack(fill="x", padx=12, pady=(0,12))

        ttk.Button(btn_frame, text="Open Folder to Index", command=self.browse_and_index).pack(side="left")

        ttk.Button(btn_frame, text="Add Command", command=self.add_command_dialog).pack(side="left", padx=6)

        ttk.Button(btn_frame, text="Close (Esc)", command=self.close).pack(side="right")


        # initial populate

        self.update_results(self.indexer.items[:50])


    def on_search_key(self, event=None):

        q = self.search_var.get()

        results = self.indexer.search(q, limit=50)

        self.update_results(results)

        # keep the first row selected

        children = self.tree.get_children()

        if children:

            self.tree.selection_set(children[0])

            self.tree.focus(children[0])


    def update_results(self, records):

        # clear

        for r in self.tree.get_children():

            self.tree.delete(r)

        for rec in records:

            self.tree.insert("", "end", values=(rec["title"], rec["path"], rec["type"]))


    def open_selected(self):

        sel = self.tree.selection()

        if not sel:

            return

        vals = self.tree.item(sel[0])["values"]

        title, path, typ = vals

        try:

            if typ == "file":

                open_path(path)

            elif typ == "cmd":

                # if it's a shell command, run it

                # Allow both simple exe names and complex shell commands

                if platform.system() == "Windows":

                    subprocess.Popen(path, shell=True)

                else:

                    subprocess.Popen(path.split(), stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)

            else:

                # fallback attempt

                open_path(path)

        except Exception as e:

            messagebox.showerror("Open failed", f"Could not open {path}\n\n{e}")

        finally:

            self.close()


    def browse_and_index(self):

        folder = filedialog.askdirectory()

        if not folder:

            return

        count = self.indexer.index_folder(folder)

        messagebox.showinfo("Indexed", f"Indexed approx {count} files from {folder}")

        # refresh results

        self.on_search_key()


    def add_command_dialog(self):

        dlg = tk.Toplevel(self)

        dlg.title("Add Command / App")

        dlg.geometry("500x150")

        tk.Label(dlg, text="Title:").pack(anchor="w", padx=8, pady=(8,0))

        title_e = ttk.Entry(dlg, width=60)

        title_e.pack(padx=8)

        tk.Label(dlg, text="Command or Path:").pack(anchor="w", padx=8, pady=(8,0))

        path_e = ttk.Entry(dlg, width=60)

        path_e.pack(padx=8)

        def add():

            t = title_e.get().strip() or Path(path_e.get()).name

            p = path_e.get().strip()

            if not p:

                messagebox.showwarning("Input", "Please provide a command or path")

                return

            typ = "cmd" if (" " in p or os.sep not in p and not Path(p).exists()) else "file"

            self.indexer.add_item(title=t, path=p, typ=typ)

            dlg.destroy()

            self.on_search_key()

        ttk.Button(dlg, text="Add", command=add).pack(pady=8)


    def close(self):

        try:

            self.grab_release()

        except:

            pass

        self.destroy()


# ------------------------------

# Main App Window

# ------------------------------

class PaletteApp:

    def __init__(self, root):

        self.root = root

        root.title("Command Palette Launcher")

        root.geometry("700x120")


        self.indexer = FileIndexer()

        self.indexer.add_common_apps()

        # Add a few demo entries (including uploaded file path)

        if Path(DEMO_FILE).exists():

            self.indexer.add_item(title=Path(DEMO_FILE).name, path=str(DEMO_FILE), typ="file")


        # Top UI

        frame = ttk.Frame(root, padding=12)

        frame.pack(fill="both", expand=True)


        ttk.Label(frame, text="Press Ctrl+P to open command palette", font=("Arial", 12)).pack(anchor="w")

        ttk.Button(frame, text="Open Palette (Ctrl+P)", command=self.open_palette).pack(pady=10, anchor="w")

        ttk.Button(frame, text="Index Folder", command=self.index_folder).pack(side="left")

        ttk.Button(frame, text="Exit", command=root.quit).pack(side="right")


        # register global hotkey in a background thread (if available)

        if KEYBOARD_AVAILABLE:

            t = threading.Thread(target=self.register_global_hotkey, daemon=True)

            t.start()

        else:

            print("keyboard package not available — global hotkey disabled. Use app's Ctrl+P instead.")


        # bind Ctrl+P inside the Tk window too

        root.bind_all("<Control-p>", lambda e: self.open_palette())


    def open_palette(self):

        # open modal CommandPalette

        cp = CommandPalette(self.root, self.indexer)


    def index_folder(self):

        folder = filedialog.askdirectory()

        if not folder:

            return

        count = self.indexer.index_folder(folder)

        messagebox.showinfo("Indexed", f"Indexed approx {count} files")


    def register_global_hotkey(self):

        """

        Register Ctrl+P as a global hotkey using keyboard module.

        When pressed, we must bring the Tk window to front and open palette.

        """

        try:

            # On some systems, keyboard requires admin privileges. If it fails, we catch and disable.

            keyboard.add_hotkey("ctrl+p", lambda: self.trigger_from_global())

            keyboard.wait()  # keep the listener alive

        except Exception as e:

            print("Global hotkey registration failed:", e)


    def trigger_from_global(self):

        # Because keyboard runs in another thread, schedule UI work in Tk mainloop

        try:

            self.root.after(0, self.open_palette)

            # Try to bring window to front

            try:

                self.root.lift()

                self.root.attributes("-topmost", True)

                self.root.after(500, lambda: self.root.attributes("-topmost", False))

            except Exception:

                pass

        except Exception as e:

            print("Error triggering palette:", e)


# ------------------------------

# Run

# ------------------------------

def main():

    root = tk.Tk()

    app = PaletteApp(root)

    root.mainloop()


if __name__ == "__main__":

    main()


AI Image Tag Generator

 """

AI Image Tag Generator (transformers + PIL)


- Uses Hugging Face transformers image-classification pipeline (ViT)

- Returns top-k labels as tags with confidence scores

- Default input path is the uploaded file: /mnt/data/image.png

"""


from transformers import pipeline

from PIL import Image

import argparse

import os


# Default path (file uploaded in this session)

DEFAULT_IMAGE_PATH = "/mnt/data/image.png"


def generate_tags(image_path, model_name="google/vit-base-patch16-224", top_k=5):

    """

    Generate tags for an image using a HF transformers image-classification pipeline.

    Returns a list of (label, score) tuples.

    """

    if not os.path.exists(image_path):

        raise FileNotFoundError(f"Image not found: {image_path}")


    classifier = pipeline("image-classification", model=model_name)

    img = Image.open(image_path).convert("RGB")

    preds = classifier(img, top_k=top_k)


    # preds is a list of dicts: [{"label": "...", "score": 0.XX}, ...]

    tags = [(p["label"], float(p["score"])) for p in preds]

    return tags


def pretty_print_tags(tags):

    print("Generated tags:")

    for label, score in tags:

        print(f" - {label}  ({score:.2f})")


def parse_args():

    p = argparse.ArgumentParser(description="AI Image Tag Generator")

    p.add_argument("--image", "-i", default=DEFAULT_IMAGE_PATH, help="Path to input image")

    p.add_argument("--model", "-m", default="google/vit-base-patch16-224", help="HuggingFace model name")

    p.add_argument("--topk", type=int, default=5, help="Number of top tags to return")

    return p.parse_args()


def main():

    args = parse_args()

    try:

        tags = generate_tags(args.image, model_name=args.model, top_k=args.topk)

        pretty_print_tags(tags)

    except Exception as e:

        print("Error:", e)


if __name__ == "__main__":

    main()


Local ML Model Trainer Interface

import streamlit as st

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns


from sklearn.model_selection import train_test_split

from sklearn.metrics import (

    accuracy_score, precision_score, recall_score, f1_score,

    mean_squared_error, confusion_matrix

)


from sklearn.preprocessing import StandardScaler


from sklearn.linear_model import LogisticRegression, LinearRegression

from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor

from sklearn.svm import SVC, SVR

from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor



st.set_page_config(page_title="Local ML Model Trainer", layout="wide")

st.title("Local ML Model Trainer Interface")

st.write("Upload a dataset → choose an algorithm → train → view results")



# ────────────────────────────────────────────────

# Upload Dataset

# ────────────────────────────────────────────────

uploaded_file = st.file_uploader("šŸ“¤ Upload CSV Dataset", type=["csv"])


if uploaded_file:

    df = pd.read_csv(uploaded_file)

    st.success("Dataset Loaded Successfully!")

    st.write("###  Data Preview")

    st.dataframe(df.head())


    st.write("###  Dataset Info")

    st.write(df.describe())


    # Target column selection

    target_col = st.selectbox(" Select Target Column (Y)", df.columns)


    # Feature columns

    X = df.drop(columns=[target_col])

    y = df[target_col]


    # Auto detect problem type

    if df[target_col].dtype == object or df[target_col].nunique() < 15:

        problem_type = "classification"

    else:

        problem_type = "regression"


    st.info(f"Detected Problem Type: **{problem_type.upper()}**")


    # Choose model based on problem type

    if problem_type == "classification":

        model_choice = st.selectbox(

            "Choose Model",

            ["Logistic Regression", "Random Forest Classifier", "SVM Classifier", "KNN Classifier"]

        )

    else:

        model_choice = st.selectbox(

            "Choose Model",

            ["Linear Regression", "Random Forest Regressor", "SVM Regressor", "KNN Regressor"]

        )


    test_size = st.slider("Test Size (Train %)", 0.1, 0.5, 0.2)


    # Train button

    if st.button(" Train Model"):

        # Preprocessing

        scaler = StandardScaler()

        X_scaled = scaler.fit_transform(X.select_dtypes(include=np.number))


        X_train, X_test, y_train, y_test = train_test_split(

            X_scaled, y, test_size=test_size, random_state=42

        )


        # Model Selection

        if model_choice == "Logistic Regression":

            model = LogisticRegression()

        elif model_choice == "Random Forest Classifier":

            model = RandomForestClassifier()

        elif model_choice == "SVM Classifier":

            model = SVC()

        elif model_choice == "KNN Classifier":

            model = KNeighborsClassifier()

        elif model_choice == "Linear Regression":

            model = LinearRegression()

        elif model_choice == "Random Forest Regressor":

            model = RandomForestRegressor()

        elif model_choice == "SVM Regressor":

            model = SVR()

        elif model_choice == "KNN Regressor":

            model = KNeighborsRegressor()


        # Train

        model.fit(X_train, y_train)

        y_pred = model.predict(X_test)


        st.success("Model Trained Successfully!")


        # ────────────────────────────────────────────────

        # Show Metrics

        # ────────────────────────────────────────────────

        st.write("## šŸ“ˆ Model Performance")


        if problem_type == "classification":

            st.write("### šŸ”¹ Classification Metrics")

            st.write(f"Accuracy: **{accuracy_score(y_test, y_pred):.4f}**")

            st.write(f"Precision: **{precision_score(y_test, y_pred, average='weighted'):.4f}**")

            st.write(f"Recall: **{recall_score(y_test, y_pred, average='weighted'):.4f}**")

            st.write(f"F1 Score: **{f1_score(y_test, y_pred, average='weighted'):.4f}**")


            # Confusion Matrix

            cm = confusion_matrix(y_test, y_pred)

            fig, ax = plt.subplots(figsize=(5, 4))

            sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", ax=ax)

            st.write("###  Confusion Matrix")

            st.pyplot(fig)


        else:

            st.write("### šŸ”¹ Regression Metrics")

            rmse = np.sqrt(mean_squared_error(y_test, y_pred))

            st.write(f"RMSE: **{rmse:.4f}**")


        # ────────────────────────────────────────────────

        # Feature Importance (for tree models)

        # ────────────────────────────────────────────────

        if "Forest" in model_choice:

            st.write("##  Feature Importance")

            importance = model.feature_importances_

            fig, ax = plt.subplots(figsize=(6, 4))

            sns.barplot(x=importance, y=X.columns, ax=ax)

            st.pyplot(fig)


 

Automatic Dataset Cleaner

#!/usr/bin/env python3

"""

Automatic Dataset Cleaner


Usage:

    python automatic_dataset_cleaner.py --file /path/to/data.csv

    python automatic_dataset_cleaner.py --file /path/to/data.csv --missing-strategy mean --outliers cap --encode --scale standard


Outputs:

    - /path/to/data_cleaned.csv           (cleaned dataset)

    - /path/to/data_cleaning_report.json  (summary of cleaning actions)

"""


import argparse

import pandas as pd

import numpy as np

import json

import os

from datetime import datetime

from sklearn.preprocessing import StandardScaler, MinMaxScaler


# ---------- Helpers ----------

def read_csv(path):

    df = pd.read_csv(path)

    return df


def save_csv(df, path):

    df.to_csv(path, index=False)


def save_json(obj, path):

    with open(path, "w", encoding="utf-8") as f:

        json.dump(obj, f, indent=2, default=str)


def summary_stats(df):

    return {

        "rows": int(df.shape[0]),

        "columns": int(df.shape[1]),

        "missing_per_column": df.isnull().sum().to_dict(),

        "dtypes": {c: str(t) for c, t in df.dtypes.items()},

        "sample_head": df.head(3).to_dict(orient="records")

    }


def auto_cast_columns(df):

    """Try to cast columns to numeric/datetime where appropriate."""

    conversions = {}

    for col in df.columns:

        if df[col].dtype == object:

            # try datetime

            try:

                parsed = pd.to_datetime(df[col], errors="coerce")

                non_null = parsed.notnull().sum()

                if non_null / max(1, len(parsed)) > 0.6:

                    df[col] = parsed

                    conversions[col] = "datetime"

                    continue

            except Exception:

                pass

            # try numeric

            coerced = pd.to_numeric(df[col].str.replace(",", "").replace(" ", ""), errors="coerce")

            if coerced.notnull().sum() / max(1, len(coerced)) > 0.6:

                df[col] = coerced

                conversions[col] = "numeric"

    return df, conversions


# ---------- Missing values ----------

def handle_missing(df, strategy="mean", fill_value=None, threshold_drop_col=0.5):

    """

    strategy: 'drop-row', 'drop-col', 'mean', 'median', 'mode', 'ffill', 'bfill', 'constant'

    threshold_drop_col: if fraction of missing > threshold, drop column

    """

    report = {"strategy": strategy, "dropped_columns": [], "details": {}}

    # drop columns with too many missing values

    missing_frac = df.isnull().mean()

    cols_to_drop = missing_frac[missing_frac > threshold_drop_col].index.tolist()

    if cols_to_drop:

        df = df.drop(columns=cols_to_drop)

        report["dropped_columns"] = cols_to_drop


    if strategy == "drop-row":

        before = len(df)

        df = df.dropna(axis=0)

        report["rows_dropped"] = before - len(df)

    elif strategy == "drop-col":

        before_cols = df.shape[1]

        df = df.dropna(axis=1)

        report["cols_dropped"] = before_cols - df.shape[1]

    elif strategy in ("mean", "median", "mode", "ffill", "bfill", "constant"):

        for col in df.columns:

            if df[col].isnull().any():

                if strategy == "mean" and pd.api.types.is_numeric_dtype(df[col]):

                    val = df[col].mean()

                    df[col] = df[col].fillna(val)

                    report["details"][col] = f"filled mean={val}"

                elif strategy == "median" and pd.api.types.is_numeric_dtype(df[col]):

                    val = df[col].median()

                    df[col] = df[col].fillna(val)

                    report["details"][col] = f"filled median={val}"

                elif strategy == "mode":

                    mode_val = df[col].mode()

                    if not mode_val.empty:

                        val = mode_val.iloc[0]

                        df[col] = df[col].fillna(val)

                        report["details"][col] = f"filled mode={val}"

                    else:

                        df[col] = df[col].fillna(fill_value)

                        report["details"][col] = f"filled mode_empty used const={fill_value}"

                elif strategy == "ffill":

                    df[col] = df[col].fillna(method="ffill").fillna(method="bfill")

                    report["details"][col] = "filled forward/backward"

                elif strategy == "bfill":

                    df[col] = df[col].fillna(method="bfill").fillna(method="ffill")

                    report["details"][col] = "filled backward/forward"

                else:  # constant

                    df[col] = df[col].fillna(fill_value)

                    report["details"][col] = f"filled const={fill_value}"

    else:

        raise ValueError("Unknown missing strategy")

    return df, report


# ---------- Outlier detection/treatment ----------

def iqr_outlier_bounds(series, k=1.5):

    q1 = series.quantile(0.25)

    q3 = series.quantile(0.75)

    iqr = q3 - q1

    low = q1 - k * iqr

    high = q3 + k * iqr

    return low, high


def handle_outliers(df, method="remove", k=1.5, numeric_only=True):

    """

    method: 'remove' (drop rows with outlier), 'cap' (clip to bounds), 'mark' (add boolean column)

    returns df, report

    """

    report = {"method": method, "columns": {}}

    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist() if numeric_only else df.columns.tolist()

    rows_before = df.shape[0]

    for col in numeric_cols:

        series = df[col].dropna()

        if series.empty:

            continue

        low, high = iqr_outlier_bounds(series, k=k)

        is_out = (df[col] < low) | (df[col] > high)

        out_count = int(is_out.sum())

        if out_count == 0:

            continue

        report["columns"][col] = {"outliers": out_count, "bounds": (float(low), float(high))}

        if method == "remove":

            df = df.loc[~is_out]

        elif method == "cap":

            df[col] = df[col].clip(lower=low, upper=high)

        elif method == "mark":

            df[f"{col}_outlier"] = is_out.astype(int)

        else:

            raise ValueError("Unknown outlier method")

    rows_after = df.shape[0]

    report["rows_before"] = int(rows_before)

    report["rows_after"] = int(rows_after)

    return df, report


# ---------- Duplicates ----------

def handle_duplicates(df, subset=None, keep="first"):

    before = df.shape[0]

    df2 = df.drop_duplicates(subset=subset, keep=keep)

    after = df2.shape[0]

    report = {"rows_before": int(before), "rows_after": int(after), "dropped": int(before-after)}

    return df2, report


# ---------- Encoding ----------

def encode_categoricals(df, one_hot=False, max_unique_for_onehot=20):

    report = {"encoded_columns": {}}

    cat_cols = df.select_dtypes(include=["category", "object"]).columns.tolist()

    if not cat_cols:

        return df, report

    for col in cat_cols:

        nunique = df[col].nunique(dropna=False)

        if one_hot and nunique <= max_unique_for_onehot:

            dummies = pd.get_dummies(df[col].astype(str), prefix=col, dummy_na=True)

            df = pd.concat([df.drop(columns=[col]), dummies], axis=1)

            report["encoded_columns"][col] = {"method": "one_hot", "new_cols": list(dummies.columns)}

        else:

            # label encoding (simple mapping)

            mapping = {val: i for i, val in enumerate(df[col].astype(str).unique())}

            df[col] = df[col].astype(str).map(mapping)

            report["encoded_columns"][col] = {"method": "label", "mapping_sample": dict(list(mapping.items())[:10])}

    return df, report


# ---------- Scaling ----------

def scale_numeric(df, method="standard"):

    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()

    report = {"method": method, "scaled_columns": numeric_cols}

    if not numeric_cols:

        return df, report

    arr = df[numeric_cols].values.astype(float)

    if method == "standard":

        scaler = StandardScaler()

    elif method == "minmax":

        scaler = MinMaxScaler()

    else:

        raise ValueError("Unknown scaling method")

    scaled = scaler.fit_transform(arr)

    df[numeric_cols] = scaled

    return df, report


# ---------- Main cleaning pipeline ----------

def clean_dataset(

    input_path,

    missing_strategy="mean",

    missing_constant=None,

    missing_drop_threshold=0.5,

    outlier_method="remove",

    outlier_k=1.5,

    outlier_numeric_only=True,

    dedupe_subset=None,

    encode=False,

    one_hot=False,

    scale_method=None

):

    # read

    df = read_csv(input_path)

    report = {"input_path": input_path, "start_time": str(datetime.now()), "initial_summary": summary_stats(df), "steps": {}}


    # auto-cast columns

    df, convs = auto_cast_columns(df)

    report["steps"]["auto_cast"] = convs


    # missing

    df, missing_report = handle_missing(df, strategy=missing_strategy, fill_value=missing_constant, threshold_drop_col=missing_drop_threshold)

    report["steps"]["missing"] = missing_report


    # duplicates

    df, dup_report = handle_duplicates(df, subset=dedupe_subset, keep="first")

    report["steps"]["duplicates"] = dup_report


    # outliers

    df, out_report = handle_outliers(df, method=outlier_method, k=outlier_k, numeric_only=outlier_numeric_only)

    report["steps"]["outliers"] = out_report


    # encode

    if encode:

        df, enc_report = encode_categoricals(df, one_hot=one_hot)

        report["steps"]["encoding"] = enc_report


    # scale

    if scale_method:

        df, scale_report = scale_numeric(df, method=scale_method)

        report["steps"]["scaling"] = scale_report


    report["final_summary"] = summary_stats(df)

    report["end_time"] = str(datetime.now())

    # output

    base, ext = os.path.splitext(input_path)

    cleaned_path = f"{base}_cleaned{ext}"

    report_path = f"{base}_cleaning_report.json"

    save_csv(df, cleaned_path)

    save_json(report, report_path)

    return cleaned_path, report_path, report


# ---------- CLI ----------

def parse_args():

    p = argparse.ArgumentParser(description="Automatic Dataset Cleaner")

    p.add_argument("--file", "-f", required=True, help="Path to CSV file")

    p.add_argument("--missing-strategy", default="mean", choices=["drop-row","drop-col","mean","median","mode","ffill","bfill","constant"], help="Missing value strategy")

    p.add_argument("--missing-constant", default=None, help="Constant value to fill missing when strategy=constant")

    p.add_argument("--missing-drop-threshold", type=float, default=0.5, help="Drop columns with missing fraction > threshold")

    p.add_argument("--outliers", default="remove", choices=["remove","cap","mark","none"], help="Outlier handling method")

    p.add_argument("--outlier-k", type=float, default=1.5, help="IQR multiplier for outlier detection")

    p.add_argument("--dedupe-subset", default=None, help="Comma separated columns to consider for duplicates (default=all columns)")

    p.add_argument("--encode", action="store_true", help="Encode categorical columns")

    p.add_argument("--one-hot", action="store_true", help="One-hot encode small cardinality categoricals (used with --encode)")

    p.add_argument("--scale", default=None, choices=["standard","minmax"], help="Scale numeric columns")

    return p.parse_args()


def main_cli():

    args = parse_args()

    dedupe_subset = args.dedupe_subset.split(",") if args.dedupe_subset else None

    outlier_method = args.outliers if args.outliers != "none" else None


    cleaned_path, report_path, report = clean_dataset(

        input_path=args.file,

        missing_strategy=args.missing_strategy,

        missing_constant=args.missing_constant,

        missing_drop_threshold=args.missing_drop_threshold,

        outlier_method=outlier_method,

        outlier_k=args.outlier_k,

        outlier_numeric_only=True,

        dedupe_subset=dedupe_subset,

        encode=args.encode,

        one_hot=args.one_hot,

        scale_method=args.scale

    )


    print("Cleaning complete.")

    print("Cleaned file:", cleaned_path)

    print("Report saved to:", report_path)

    # Also print a short summary

    print(json.dumps({

        "rows_before": report["initial_summary"]["rows"],

        "rows_after": report["final_summary"]["rows"],

        "columns_before": report["initial_summary"]["columns"],

        "columns_after": report["final_summary"]["columns"],

        "missing_info": report["initial_summary"]["missing_per_column"]

    }, indent=2))


if __name__ == "__main__":

    main_cli()

 

Local Chat App Over LAN (Socket-Based)

 chat_server.py

import socket

import threading


HOST = "0.0.0.0"     # Accept connections from LAN

PORT = 5000


clients = []

usernames = {}


# Broadcast message to all connected clients

def broadcast(msg, sender_conn=None):

    for client in clients:

        if client != sender_conn:

            try:

                client.send(msg.encode())

            except:

                pass


def handle_client(conn, addr):

    print(f"[NEW CONNECTION] {addr}")


    try:

        username = conn.recv(1024).decode()

        usernames[conn] = username


        broadcast(f" {username} joined the chat!")

        print(f"User '{username}' connected.")


        while True:

            msg = conn.recv(1024).decode()

            if not msg:

                break


            full_msg = f"{username}: {msg}"

            print(full_msg)

            broadcast(full_msg, conn)


    except Exception as e:

        print("Error:", e)


    finally:

        print(f"{addr} disconnected")

        clients.remove(conn)

        broadcast(f"{usernames[conn]} left the chat.")

        conn.close()


def start_server():

    server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

    server.bind((HOST, PORT))

    server.listen()


    print(f"Server started on {socket.gethostbyname(socket.gethostname())}:{PORT}")


    while True:

        conn, addr = server.accept()

        clients.append(conn)


        thread = threading.Thread(target=handle_client, args=(conn, addr))

        thread.daemon = True

        thread.start()


if __name__ == "__main__":

    start_server()

chat_client.py

import socket
import threading
import tkinter as tk
from tkinter import scrolledtext, messagebox

class ChatClient:
    def __init__(self, root):
        self.root = root
        root.title("LAN Chat Client")
        root.geometry("400x500")

        tk.Label(root, text="Server IP:").pack()
        self.ip_entry = tk.Entry(root)
        self.ip_entry.pack()

        tk.Label(root, text="Username:").pack()
        self.username_entry = tk.Entry(root)
        self.username_entry.pack()

        tk.Button(root, text="Connect", command=self.connect_server).pack(pady=10)

        self.chat_area = scrolledtext.ScrolledText(root, state="disabled")
        self.chat_area.pack(expand=True, fill="both", pady=10)

        self.msg_entry = tk.Entry(root)
        self.msg_entry.pack(fill="x")

        tk.Button(root, text="Send", command=self.send_message).pack(pady=5)

        self.sock = None
        self.running = False

    def connect_server(self):
        ip = self.ip_entry.get()
        username = self.username_entry.get()

        if not ip or not username:
            messagebox.showerror("Error", "Enter IP and Username!")
            return

        try:
            self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            self.sock.connect((ip, 5000))
            self.sock.send(username.encode())
        except:
            messagebox.showerror("Error", "Cannot connect to server!")
            return

        self.running = True
        threading.Thread(target=self.receive_messages, daemon=True).start()
        self.chat_area.config(state="normal")
        self.chat_area.insert("end", "Connected!\n")
        self.chat_area.config(state="disabled")

    def receive_messages(self):
        while self.running:
            try:
                msg = self.sock.recv(1024).decode()
                if msg:
                    self.chat_area.config(state="normal")
                    self.chat_area.insert("end", msg + "\n")
                    self.chat_area.yview("end")
                    self.chat_area.config(state="disabled")
            except:
                break

    def send_message(self):
        msg = self.msg_entry.get()
        if msg and self.sock:
            try:
                self.sock.send(msg.encode())
                self.msg_entry.delete(0, tk.END)
            except:
                pass

    def on_close(self):
        self.running = False
        if self.sock:
            self.sock.close()
        self.root.destroy()

if __name__ == "__main__":
    root = tk.Tk()
    client = ChatClient(root)
    root.protocol("WM_DELETE_WINDOW", client.on_close)
    root.mainloop()

Library Book Borrowing System

 """

Library Book Borrowing System (Tkinter + SQLite)

Features:

- User Login / Register

- Admin Login

- Borrow / Return Books

- Due Date Tracking

- Overdue Alerts

"""


import sqlite3

import tkinter as tk

from tkinter import ttk, messagebox

from datetime import datetime, timedelta


DB = "library.db"


# ----------------- DATABASE SETUP -----------------

def init_db():

    conn = sqlite3.connect(DB)

    c = conn.cursor()


    # Users Table

    c.execute("""

        CREATE TABLE IF NOT EXISTS users (

            id INTEGER PRIMARY KEY AUTOINCREMENT,

            username TEXT UNIQUE,

            password TEXT,

            role TEXT

        )

    """)


    # Books Table

    c.execute("""

        CREATE TABLE IF NOT EXISTS books (

            id INTEGER PRIMARY KEY AUTOINCREMENT,

            title TEXT,

            author TEXT,

            available INTEGER DEFAULT 1

        )

    """)


    # Borrow Table

    c.execute("""

        CREATE TABLE IF NOT EXISTS borrowed (

            id INTEGER PRIMARY KEY AUTOINCREMENT,

            user_id INTEGER,

            book_id INTEGER,

            borrowed_date TEXT,

            due_date TEXT,

            FOREIGN KEY(user_id) REFERENCES users(id),

            FOREIGN KEY(book_id) REFERENCES books(id)

        )

    """)


    # Default admin

    c.execute("SELECT * FROM users WHERE role='admin'")

    if not c.fetchone():

        c.execute("INSERT INTO users(username, password, role) VALUES('admin','admin','admin')")

        print("Default admin created: admin / admin")


    conn.commit()

    conn.close()


# ----------------- LOGIN WINDOW -----------------

class LoginWindow:

    def __init__(self, root):

        self.root = root

        root.title("Library System - Login")

        root.geometry("350x250")


        tk.Label(root, text="Username:", font=("Arial", 12)).pack(pady=5)

        self.username_entry = tk.Entry(root)

        self.username_entry.pack()


        tk.Label(root, text="Password:", font=("Arial", 12)).pack(pady=5)

        self.password_entry = tk.Entry(root, show="*")

        self.password_entry.pack()


        tk.Button(root, text="Login", command=self.login).pack(pady=10)

        tk.Button(root, text="Register", command=self.register).pack()


    def login(self):

        username = self.username_entry.get()

        password = self.password_entry.get()


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("SELECT * FROM users WHERE username=? AND password=?", (username, password))

        user = c.fetchone()

        conn.close()


        if user:

            role = user[3]

            if role == "admin":

                AdminDashboard(tk.Toplevel(), user)

            else:

                UserDashboard(tk.Toplevel(), user)

        else:

            messagebox.showerror("Error", "Invalid credentials!")


    def register(self):

        RegisterWindow(tk.Toplevel())


# ----------------- REGISTER WINDOW -----------------

class RegisterWindow:

    def __init__(self, root):

        self.root = root

        root.title("Register")

        root.geometry("300x250")


        tk.Label(root, text="Create Username").pack(pady=5)

        self.user_entry = tk.Entry(root)

        self.user_entry.pack()


        tk.Label(root, text="Create Password").pack(pady=5)

        self.pass_entry = tk.Entry(root, show="*")

        self.pass_entry.pack()


        tk.Button(root, text="Register", command=self.register_user).pack(pady=10)


    def register_user(self):

        username = self.user_entry.get()

        password = self.pass_entry.get()


        conn = sqlite3.connect(DB)

        c = conn.cursor()


        try:

            c.execute("INSERT INTO users(username,password,role) VALUES(?,?,?)",

                      (username, password, "user"))

            conn.commit()

            messagebox.showinfo("Success", "Registration complete!")

            self.root.destroy()

        except:

            messagebox.showerror("Error", "Username already exists.")

        conn.close()


# ----------------- ADMIN DASHBOARD -----------------

class AdminDashboard:

    def __init__(self, root, user):

        self.root = root

        root.title("Admin Dashboard")

        root.geometry("600x500")


        tk.Label(root, text="Admin Dashboard", font=("Arial", 16)).pack(pady=10)


        tk.Button(root, text="Add Book", width=20, command=self.add_book_window).pack(pady=5)

        tk.Button(root, text="Remove Book", width=20, command=self.remove_book_window).pack(pady=5)

        tk.Button(root, text="View All Books", width=20, command=self.view_books).pack(pady=5)

        tk.Button(root, text="View Users", width=20, command=self.view_users).pack(pady=5)


    def add_book_window(self):

        win = tk.Toplevel()

        win.title("Add Book")

        win.geometry("300x200")


        tk.Label(win, text="Title").pack()

        title = tk.Entry(win)

        title.pack()


        tk.Label(win, text="Author").pack()

        author = tk.Entry(win)

        author.pack()


        def save():

            conn = sqlite3.connect(DB)

            c = conn.cursor()

            c.execute("INSERT INTO books(title, author) VALUES(?,?)", (title.get(), author.get()))

            conn.commit()

            conn.close()

            messagebox.showinfo("Success", "Book Added!")

            win.destroy()


        tk.Button(win, text="Save", command=save).pack(pady=10)


    def remove_book_window(self):

        win = tk.Toplevel()

        win.title("Remove Book")

        win.geometry("300x200")


        tk.Label(win, text="Book ID").pack()

        book_id = tk.Entry(win)

        book_id.pack()


        def delete():

            conn = sqlite3.connect(DB)

            c = conn.cursor()

            c.execute("DELETE FROM books WHERE id=?", (book_id.get(),))

            conn.commit()

            conn.close()

            messagebox.showinfo("Removed", "Book deleted!")

            win.destroy()


        tk.Button(win, text="Delete", command=delete).pack(pady=10)


    def view_books(self):

        BookListWindow(tk.Toplevel(), admin=True)


    def view_users(self):

        UsersListWindow(tk.Toplevel())


# ----------------- USER DASHBOARD -----------------

class UserDashboard:

    def __init__(self, root, user):

        self.root = root

        self.user = user

        root.title("User Dashboard")

        root.geometry("600x500")


        tk.Label(root, text=f"Welcome {user[1]}", font=("Arial", 16)).pack(pady=10)


        tk.Button(root, text="Borrow Book", width=20, command=self.borrow_window).pack(pady=10)

        tk.Button(root, text="Return Book", width=20, command=self.return_window).pack(pady=10)

        tk.Button(root, text="My Borrowed Books", width=20, command=self.my_books).pack(pady=10)


        self.check_due_alerts()


    def borrow_window(self):

        BookListWindow(tk.Toplevel(), user=self.user)


    def return_window(self):

        ReturnBookWindow(tk.Toplevel(), self.user)


    def my_books(self):

        UserBorrowedBooks(tk.Toplevel(), self.user)


    def check_due_alerts(self):

        conn = sqlite3.connect(DB)

        c = conn.cursor()

        today = datetime.now()


        c.execute("""SELECT books.title, borrowed.due_date 

                     FROM borrowed 

                     JOIN books ON books.id = borrowed.book_id 

                     WHERE borrowed.user_id=?""",

                  (self.user[0],))

        rows = c.fetchall()

        conn.close()


        alerts = []

        for title, due_date in rows:

            due = datetime.strptime(due_date, "%Y-%m-%d")

            days_left = (due - today).days


            if days_left < 0:

                alerts.append(f"OVERDUE: {title} (Due {due_date})")

            elif days_left <= 2:

                alerts.append(f"Due Soon: {title} (Due {due_date})")


        if alerts:

            messagebox.showwarning("Due Date Alerts", "\n".join(alerts))


# ----------------- BOOK LIST WINDOW -----------------

class BookListWindow:

    def __init__(self, root, admin=False, user=None):

        self.root = root

        self.user = user

        root.title("Books List")

        root.geometry("600x400")


        columns = ("ID","Title","Author","Available")

        tree = ttk.Treeview(root, columns=columns, show="headings")

        for col in columns:

            tree.heading(col, text=col)

        tree.pack(fill="both", expand=True)


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("SELECT * FROM books")

        rows = c.fetchall()

        conn.close()


        for r in rows:

            tree.insert("", tk.END, values=r)


        if user:  

            tk.Button(root, text="Borrow Selected", command=lambda: self.borrow(tree)).pack(pady=10)


    def borrow(self, tree):

        selected = tree.focus()

        if not selected:

            messagebox.showwarning("Select", "Select a book first!")

            return


        values = tree.item(selected)["values"]

        book_id, title, author, available = values


        if available == 0:

            messagebox.showerror("Unavailable", "Book already borrowed!")

            return


        due = (datetime.now() + timedelta(days=7)).strftime("%Y-%m-%d")


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("UPDATE books SET available=0 WHERE id=?", (book_id,))

        c.execute("INSERT INTO borrowed(user_id, book_id, borrowed_date, due_date) VALUES(?,?,?,?)",

                  (self.user[0], book_id, datetime.now().strftime("%Y-%m-%d"), due))

        conn.commit()

        conn.close()


        messagebox.showinfo("Success", f"Book borrowed! Due on {due}")

        self.root.destroy()


# ----------------- RETURN BOOK WINDOW -----------------

class ReturnBookWindow:

    def __init__(self, root, user):

        self.root = root

        self.user = user

        root.title("Return Book")

        root.geometry("500x350")


        columns = ("Borrow ID","Book Title","Due Date")

        self.tree = ttk.Treeview(root, columns=columns, show="headings")

        for col in columns:

            self.tree.heading(col, text=col)

        self.tree.pack(fill="both", expand=True)


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("""SELECT borrowed.id, books.title, borrowed.due_date

                     FROM borrowed 

                     JOIN books ON books.id = borrowed.book_id 

                     WHERE borrowed.user_id=?""",

                  (user[0],))

        rows = c.fetchall()

        conn.close()


        for r in rows:

            self.tree.insert("", tk.END, values=r)


        tk.Button(root, text="Return Selected", command=self.return_book).pack(pady=10)


    def return_book(self):

        selected = self.tree.focus()

        if not selected:

            messagebox.showwarning("Select", "Select a book!")

            return


        borrow_id, title, due = self.tree.item(selected)["values"]


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("SELECT book_id FROM borrowed WHERE id=?", (borrow_id,))

        book_id = c.fetchone()[0]


        c.execute("DELETE FROM borrowed WHERE id=?", (borrow_id,))

        c.execute("UPDATE books SET available=1 WHERE id=?", (book_id,))

        conn.commit()

        conn.close()


        messagebox.showinfo("Returned", f"{title} returned successfully!")

        self.root.destroy()


# ----------------- USER BORROWED LIST -----------------

class UserBorrowedBooks:

    def __init__(self, root, user):

        self.root = root

        root.title("My Borrowed Books")

        root.geometry("600x350")


        columns = ("Book Title","Borrowed Date","Due Date")

        tree = ttk.Treeview(root, columns=columns, show="headings")

        for col in columns:

            tree.heading(col, text=col)

        tree.pack(fill="both", expand=True)


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("""SELECT books.title, borrowed.borrowed_date, borrowed.due_date

                     FROM borrowed 

                     JOIN books ON books.id = borrowed.book_id 

                     WHERE borrowed.user_id=?""",

                  (user[0],))

        rows = c.fetchall()

        conn.close()


        for r in rows:

            tree.insert("", tk.END, values=r)


# ----------------- USERS LIST WINDOW (ADMIN) -----------------

class UsersListWindow:

    def __init__(self, root):

        root.title("All Users")

        root.geometry("600x300")


        columns = ("ID","Username","Role")

        tree = ttk.Treeview(root, columns=columns, show="headings")

        for col in columns:

            tree.heading(col, text=col)

        tree.pack(fill="both", expand=True)


        conn = sqlite3.connect(DB)

        c = conn.cursor()

        c.execute("SELECT id, username, role FROM users")

        rows = c.fetchall()

        conn.close()


        for r in rows:

            tree.insert("", tk.END, values=r)


# ----------------- MAIN APP -----------------

if __name__ == "__main__":

    init_db()

    root = tk.Tk()

    LoginWindow(root)

    root.mainloop()