In this homework assignment you will use census data from the 1994 and 1995 current population surveys conducted by the U.S. Census Bureau. A copy of this dataset is located at UCI Machine Learning
Need help with Python programming
In this homework assignment you will use census data from the 1994 and 1995 current population surveys conducted by the U.S. Census Bureau. A copy of this dataset is located at UCI Machine Learning repository, please see this link to reach to the dataset website. This dataset contains census data extracted from the 1994 and 1995 Current Population Surveys. We will only work with ‘training’ data (a link to that is provided to you below). The data contains 41 demographic and employment related variables. The abbreviated column names provided to you below. You are expected to read the documentation of this dataset, understand the features and preprocess this dataset. Additional information can be found in the data description and additional comments. Below you will find a code snippet to download and read the data into a pandas dataframe. You can alternatively download it yourself, extract and read it manually. The questions are shown in the subsequent cells. You can provide your answers in this file. Make sure to change the notebook’s name and add your name before submitting.
### Q1 – Identify the data scales and data types for each variable in census data. Identify the domain for each variable by checking the attributes’ values. Then, create a data quality report for both categorical (nominal, ordinal) and continuous (interval, ratio) variables. For data scales, identify whether an attribute is nominal, ordinal, interval or ratio scale. For data types, identify the domain and provide an appropriate data type (integer, float, String, date, Boolean). See if that data type is correct in your dataframe. For domain, inspect each distinct value for each attribute. Identify missing values. Also include the bar plots and histograms for visualizing the distributions. The examples for a continious and a categorical feature can be seen below. You do not need to use jupyter formatting provided here. You can print a DataFrame or read a csv, and display it. Make sure you have the csv in your zip file.
Q2 – Identify the data quality issues for each attribute. Create a data quality plan and implement the changes. Identify missing values, potential anomalies and outliers. Finally, remedy these issues.
Q3 – For all the interval and ratio scale features, create a scatter plot matrix (pairplots) and correlation matrix. For all ordinal scale features, create a correlation matrix using Spearman correlation. Use the data scales list you created in when creating a correlation matrix using Spearman rank, please use all features having an order (i.e., ordinal, interval, ratio scale variables) and not just ordinal features.