edit broken links

Author: khuyentran1401

README.md

@@ -29,12 +29,12 @@ This repository is a curated collection of data science articles from CodeCut, c
 | Python Helper Tools   | Write Clean Python Code Using Pipes                                             | [🔗](https://codecut.ai/write-clean-python-code-using-pipes-3/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                                            | [🔗](https://deepnote.com/project/Data-science-hxlyJpi-QrKFJziQgoMSmQ/%2FData-science%2Fproductive_tools%2Fpipe.ipynb)    | [🔗](https://youtu.be/K20_eZZGqsc)                                             |
 | Python Helper Tools   | Introducing FugueSQL — SQL for Pandas, Spark, and Dask DataFrames               | [🔗](https://codecut.ai/introducing-fuguesql-sql-for-pandas-spark-and-dask-dataframes-2/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                  | [🔗](https://github.com/khuyentran1401/Data-science/blob/master/data_science_tools/fugueSQL.ipynb)                        |                                                                                |
 | Python Helper Tools   | Fugue and DuckDB: Fast SQL Code in Python                                       | [🔗](https://codecut.ai/fugue-and-duckdb-fast-sql-code-in-python-2/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                                       | [🔗](https://github.com/khuyentran1401/Data-science/blob/master/productive_tools/Fugue_and_Duckdb/Fugue_and_Duckdb.ipynb) |                                                                                |
-| Feature Engineering   | Polars vs. Pandas: A Fast, Multi-Core Alternative for DataFrames                | [🔗](https://codecut.ai/polars-vs-pandas-a-fast-multi-core-alternative-for-dataframes/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                    | [🔗](https://khuyentran1401.github.io/Data-science/data_science_tools/polars_vs_pandas.html)                              |                                                                                |
+| Feature Engineering   | Polars vs. Pandas: A Fast, Multi-Core Alternative for DataFrames                | [🔗](https://codecut.ai/polars-vs-pandas-a-fast-multi-core-alternative-for-dataframes/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                    | [🔗](https://codecuttech.github.io/Data-science/data_science_tools/polars_vs_pandas.html)                              |                                                                                |
 | Visualization         | Top 6 Python Libraries for Visualization: Which one to Use?                     | [🔗](https://codecut.ai/top-6-python-libraries-for-visualization-which-one-to-use/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                        | [🔗](https://github.com/khuyentran1401/Data-science/tree/master/visualization/top_visualization.ipynb)                    |                                                                                |
 | Python                | Python Clean Code: 6 Best Practices to Make Your Python Functions More Readable | [🔗](https://codecut.ai/python-clean-code-6-best-practices-to-make-your-python-functions-more-readable-2/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog) | [🔗](https://github.com/khuyentran1401/Data-science/tree/master/python/good_functions)                                    | [🔗](https://youtu.be/IDHD8JYBl5M)                                             |
 | Logging and Debugging | Loguru: Simple as Print, Flexible as Logging                                    | [🔗](https://codecut.ai/simplify-your-python-logging-with-loguru/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                                         | [🔗](https://github.com/khuyentran1401/Data-science/tree/master/productive_tools/logging_tools)                           | [🔗](https://youtu.be/XY_OrUoR-HU)                                             |
-| LLM                   | Enforce Structured Outputs from LLMs with PydanticAI                            | [🔗](https://codecut.ai/enforce-structured-outputs-from-llms-with-pydanticai/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                             | [🔗](https://khuyentran1401.github.io/Data-science/llm/pydantic_ai_examples.html)                                         |                                                                                |
-| Speed-up Tools        | Writing Safer PySpark Queries with Parameters                                   | [🔗](https://codecut.ai/pyspark-sql-enhancing-reusability-with-parameterized-queries/)                                                                                      | [🔗](https://khuyentran1401.github.io/Data-science/data_science_tools/pandas_api_on_spark.html)                           |                                                                                |
+| LLM                   | Enforce Structured Outputs from LLMs with PydanticAI                            | [🔗](https://codecut.ai/enforce-structured-outputs-from-llms-with-pydanticai/?utm_source=github&utm_medium=data_science_repo&utm_campaign=blog)                             | [🔗](https://codecuttech.github.io/Data-science/llm/pydantic_ai_examples.html)                                         |                                                                                |
+| Speed-up Tools        | Writing Safer PySpark Queries with Parameters                                   | [🔗](https://codecut.ai/pyspark-sql-enhancing-reusability-with-parameterized-queries/)                                                                                      | [🔗](https://codecuttech.github.io/Data-science/data_science_tools/pandas_api_on_spark.html)                           |                                                                                |
 
 
 ## Contributing