Spaces:
Sleeping
Sleeping
File size: 3,725 Bytes
9b5b26a c19d193 6aae614 8fe992b 9b5b26a 5df72d6 49c86fd 9b5b26a 49c86fd 9b5b26a 49c86fd 9b5b26a 8c01ffb 6aae614 ae7a494 e121372 bf6d34c 29ec968 fe328e0 13d500a 8c01ffb 9b5b26a 8c01ffb 861422e 9b5b26a 8c01ffb 8fe992b 49c86fd 8c01ffb 861422e 8fe992b 9b5b26a 8c01ffb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from Gradio_UI import GradioUI
# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def generate_data_science_steps(process: str) -> str:
"""A tool that generates concise step-by-step instructions for a given data science process.
Args:
process: The name of the data science process (e.g., "Data Cleaning", "Feature Engineering", "Model Training").
Returns:
A concise list of steps for executing the specified process.
"""
steps_dict = {
"data cleaning": [
"1. Load the dataset.",
"2. Handle missing values (impute or remove).",
"3. Remove duplicates.",
"4. Fix inconsistent data types.",
"5. Normalize/standardize data if needed."
],
"feature engineering": [
"1. Identify relevant features.",
"2. Create new features from existing data.",
"3. Encode categorical variables.",
"4. Scale numerical features.",
"5. Select the most important features."
],
"model training": [
"1. Split data into train/test sets.",
"2. Choose an appropriate algorithm.",
"3. Train the model on training data.",
"4. Evaluate using validation data.",
"5. Tune hyperparameters for better performance."
],
"data visualization": [
"1. Choose the right visualization type.",
"2. Load and preprocess data.",
"3. Use libraries like Matplotlib or Seaborn.",
"4. Label axes and titles for clarity.",
"5. Interpret insights from the visuals."
]
}
process = process.lower()
if process in steps_dict:
return "\n".join(steps_dict[process])
else:
return f"Sorry, I don't have predefined steps for '{process}'. Try another data science process."
@tool
def get_current_time_in_timezone(timezone: str) -> str:
"""A tool that fetches the current local time in a specified timezone.
Args:
timezone: A string representing a valid timezone (e.g., 'America/New_York').
"""
try:
# Create timezone object
tz = pytz.timezone(timezone)
# Get current time in that timezone
local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
return f"The current local time in {timezone} is: {local_time}"
except Exception as e:
return f"Error fetching time for timezone '{timezone}': {str(e)}"
final_answer = FinalAnswerTool()
# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud'
model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)
# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
with open("prompts.yaml", 'r') as stream:
prompt_templates = yaml.safe_load(stream)
agent = CodeAgent(
model=model,
tools=[final_answer,generate_data_science_steps], ## add your tools here (don't remove final answer)
max_steps=6,
verbosity_level=1,
grammar=None,
planning_interval=None,
name=None,
description=None,
prompt_templates=prompt_templates
)
GradioUI(agent).launch() |