Performed end-to-end data cleaning and exploratory data analysis (EDA) on a structured dataset using Python and Pandas. The project simulates the first phase of any real-world data analytics workflow — assessing data quality, resolving issues, and preparing a clean dataset ready for analysis or modeling.
Tools: Python · Pandas · NumPy · Jupyter Notebook
- What does the dataset structure look like and are the data types correct?
- Where are the missing values and how should they be handled?
- What does the distribution of key fields look like?
- Is the dataset clean and ready for downstream analysis?
Loaded the dataset into a Pandas DataFrame and performed an initial inspection to understand its structure, column types, and overall shape.
df = pd.read_csv('Week2_Part1_Data_Cleaning.ipynb')
df.head()
df.info()
df.describe()Identified columns with null values and quantified the extent of missing data across the dataset to determine the appropriate cleaning strategy.
Reviewed and corrected column data types to ensure numeric, categorical, and date fields were properly formatted for analysis.
Applied cleaning techniques to handle missing values, remove duplicates, and standardize fields — producing a clean, analysis-ready dataset.
Validated the cleaned dataset structure before exporting for downstream use.
- Data loading and inspection with Pandas
- Missing value detection and handling
- Data type validation and correction
- Exploratory data analysis (EDA)
- Data cleaning and preprocessing
- Jupyter Notebook workflow management
| File | Description |
|---|---|
Week2_Part1_Data_Cleaning.ipynb |
Main Jupyter Notebook with full workflow |
df_isnull.png |
Missing values analysis output |
df_labeling.png |
Cleaned dataset preview |
Successfully assessed and cleaned the dataset, resolving missing values and data type inconsistencies. The cleaned dataset was validated and prepared for downstream exploratory analysis and visualization.
Eddy Bartolome
Data Analyst | Python · SQL · Power BI · Excel
LinkedIn ·
GitHub