genearate_users.py

import numpy as np
import google.generativeai as palm
import pandas as pd
import os
import json
import re
import random
from faker import Faker

fake = Faker()

palm.configure(api_key='AIzaSyDnUxKaSdabi0rNjxdcKtSvSuKWE-zDkNo')
path = "C:/Users/limah/OneDrive/Desktop/nasaSpaceApp/users.json"

programming_skills = [
    "Python", "JavaScript", "Java", "C++", "Ruby", "Swift", "PHP", "Go", "Rust", "SQL",
    "C#", "Perl", "HTML/CSS", "Kotlin", "TypeScript", "Scala", "Matlab", "R", "Assembly"
]

space_skills = [
    "Astrophysics", "Astronomy", "Space Exploration", "Rocket Science", "Planetary Science", "Astrobiology",
    "Orbital Mechanics", "Astrochemistry", "Exoplanet Research", "Space Weather", "Telescope Operation"
]

general_skills = [
    "Communication", "Problem Solving", "Time Management", "Teamwork", "Critical Thinking", "Leadership",
    "Project Management", "Data Analysis", "Creativity", "Adaptability", "Networking", "Public Speaking"
]


def generate_user():
    name = fake.name()
    email = fake.email()
    programming_skill = random.choice(programming_skills)
    space_skill = random.choice(space_skills)
    general_skill = random.choice(general_skills)
    description = f"I am good at {programming_skill} and  {space_skill} and  {general_skill}"
    return {
        "Name": name,
        "Email": email,
        "Description": description
    }


def get_embedding(skills):
  model = "models/embedding-gecko-001"
  x = skills
  embedding = palm.generate_embeddings(model=model, text=x)
  embedding = embedding['embedding']
  return embedding


def save_skills(existing_data, name, skills, embedding, email):
#   if existing_data == None:
#     existing_data = pd.DataFrame()
#     print("::yessss")
  new_row_data = {'name': name, 'skills': skills, 'email' :email, 'embeddings' : f"{embedding}"}        
  new_row_df = pd.DataFrame(new_row_data, index=[0])
  existing_data = pd.concat([existing_data, new_row_df], ignore_index=True)
  existing_data.to_json(path)
  # new_row_df.to_json(path, orient='records')
  print("saved")


users = [generate_user() for _ in range(20)]
for idx, user in enumerate(users, start=1):
    existing_data = pd.read_json(path)
    skills =user["Description"]
    name = user["Name"]
    email = user["Email"]
    embedding  = get_embedding(skills)
    save_skills(existing_data, name,skills, embedding, email)