TechSpark_AI / data.py
aslan-ng's picture
Update data.py
9d8cc6b verified
# Imports
from datasets import load_dataset
from huggingface_hub import login
from settings import *
# Load Data
NUMERIC_PROFILE = ["Laser Cutting", "Wood Working", "Wood CNC", "Metal Machining", "Metal CNC", "3D Printer", "Welding", "Electronics"]
login(HF_TOKEN)
def load_data_from_huggingface():
"""
Loads data from HuggingFace.
"""
# Staff (People)
ds_staff = load_dataset(REPO_ID_TECHSPARK_STAFF)
staff_df = ds_staff["train"].to_pandas()
# Courses
ds_courses = load_dataset(REPO_ID_TECHSPARK_COURSES)
courses_df = ds_courses["train"].to_pandas()
# Tools
ds_tools = load_dataset(REPO_ID_TECHSPARK_TOOLS)
tools_df = ds_tools["train"].to_pandas()
# Map Nodes
ds_nodes = load_dataset(REPO_ID_TECHSPARK_MAP_NODES)
nodes_df = ds_nodes["train"].to_pandas()
# Map Edges
ds_edges = load_dataset(REPO_ID_TECHSPARK_MAP_EDGES)
edges_df = ds_edges["train"].to_pandas()
return staff_df, courses_df, tools_df, nodes_df, edges_df
staff_df, courses_df, tools_df, nodes_df, edges_df = load_data_from_huggingface()