Download eda.py from Rishe7/Databot: direct link, hf CLI and curl.
- Browser
- Download file 1.68 kB
-
https://huggingface.co/Rishe7/Databot/resolve/main/eda.py
- Command line
-
hf download hf://Rishe7/Databot/eda.py
-
curl -L -o eda.py https://huggingface.co/Rishe7/Databot/resolve/main/eda.py
1.68 kB
| import pandas as pd | |
| import sweetviz as sv | |
| from tools.dataframe import get_dataframe_summary | |
| from typing import Tuple, Dict | |
| import os | |
| import tempfile | |
| def explain_data(data_raw, n_sample= 10) -> str: | |
| """ | |
| Tool: explain_data | |
| Description: | |
| Provides an extensive, narrative summary of a DataFrame including its shape, column types, | |
| missing value percentages, unique counts, sample rows, and (if not skipped) descriptive stats/info. | |
| Parameters: | |
| data_raw (dict): Raw data. | |
| n_sample (int, default=30): Number of rows to display. | |
| skip_stats (bool, default=False): If True, omit descriptive stats/info. | |
| LLM Guidance: | |
| Use when a detailed, human-readable explanation is needed—i.e., a full overview is preferred over a concise numerical summary. | |
| Returns: | |
| str: Detailed DataFrame summary. | |
| """ | |
| print(" * Tool: explain_data") | |
| import pandas as pd | |
| result = get_dataframe_summary( | |
| pd.DataFrame(data_raw), n_sample=10, skip_stats=False | |
| ) | |
| return result | |
| def generate_sweetviz_report( | |
| data_raw: dict, | |
| target: str = None, | |
| report_name: str = "Report.html", | |
| report_directory: str = None, | |
| open_browser: bool = False, | |
| ) -> Tuple[str, Dict]: | |
| df = pd.DataFrame(data_raw) | |
| analysis = sv.analyze(df, target_feat=target) | |
| if report_directory is None: | |
| report_directory = tempfile.mkdtemp() | |
| report_path = os.path.join(report_directory, report_name) | |
| analysis.show_html(filepath=report_path, open_browser=open_browser) | |
| return ( | |
| f"Press on the download report button at the bottom", | |
| {"report_path": report_path}, | |
| ) |