This dataset contains information about individuals, including demographic attributes such as age, education, occupation, etc., as well as whether their income exceeds $50K per year. The dataset is useful for various types of analyses, including demographic studies, income prediction modeling, and exploratory data analysis.
- Format: CSV (Comma Separated Values)
- Columns:
- age: Age of the individual.
- workclass: Type of employer the individual works for.
- fnlwgt: Final weight used in sampling.
- education: Highest level of education achieved.
- educational-num: Numerical representation of education.
- marital-status: Marital status of the individual.
- occupation: Type of occupation.
- relationship: Relationship status.
- race: Race of the individual.
- gender: Gender of the individual.
- capital-gain: Capital gains of the individual.
- capital-loss: Capital losses of the individual.
- hours-per-week: Number of hours worked per week.
- native-country: Country of origin.
- income_>50K: Binary indicator of whether the individual's income exceeds $50K per year.
- Descriptive Statistics: Compute summary statistics for numerical columns (e.g., mean, median, standard deviation) and frequency distributions for categorical columns.
- Data Cleaning: Check for missing values, outliers, and inconsistencies in the data. Handle them appropriately.
- Exploratory Data Analysis (EDA): Explore relationships between different variables using visualizations (e.g., histograms, bar plots, scatter plots).
- Feature Engineering: Create new features if necessary, derive insights from existing features.
- Income Prediction Modeling: Build predictive models to predict whether an individual's income exceeds $50K per year based on available attributes. Evaluate model performance using appropriate metrics (e.g., accuracy, precision, recall).
- Feature Importance: Determine which features have the most significant impact on predicting income levels.
- Ethnicity and Gender Analysis: Explore any disparities in income levels based on ethnicity and gender.
- Python
- Pandas
- NumPy
- Matplotlib
- Scikit-learn
- Seaborn
- statsmodels.api
- Nirbhay