The dataset you will use is a CSV file that contains housing data collected from the...

   

Transcribed Image Text:

The dataset you will use is a CSV file that contains housing data collected from the 1990 California census. You can find this dataset on Kaggle at https://www.kaggle.com/datasets/cammugent/california- housing-prices. Homework Steps The homework is out of 30 total points, all shown here below. 1. Load the dataset into a Pandas DataFrame. (1 pts) 2. Print out all the data in the first 5 and last 5 rows. (2 pts) 3. Print out the type, Non-Null count, and name of each column. (2 pts) 4. Write at least 3 of the potential dataset biases or issues you could see persisting, in a multi-line comment at the top of your program. (2 pts) 5. Print the count, mean, standard deviation, minimum, 25%, 50%, 75%, and maximum values of all the radial data. (2 pts) 6. Print out the count, unique count, mode, and frequency of the mode of the ordinal and nominal data (all have the Pandas type as object) (1 pt) 7. Plot a histogram of each numerical value in a single figure using subplots, or the hist() function in Pandas (much easier option of the two, needs just one line). (2 pt) 8. Print the mean "median house value" grouped by the "median age" in sorted order. (2 pt) 9. Plot every latitude and longitude in a scatter plot. (2 pts) 10. Using Seaborn, plot a histogram of "median house value with columns for each value of "ocean proximity". (1 pt) 11. Plot every latitude and longitude in a scatter plot, with the point weight being their value for "median house value". (1 pt) 12. Create a temporary DataFrame, and remove all rows that are not <1H Ocean". It should now be the only category remaining in this temporary DataFrame. Now, scatter plot all of these latitudes and longitudes, with the "median house value" as the point weight. (2 pts) 13. Re-using the temporary DataFrame made in the last question, apply a mask to remove any "median income values under 300,000. Plot the now masked latitude and longitudes as a scatter plot, again with point weight being the "median house value". You will no longer use the temporary DataFrame after this question. (2 pts) 14. Create and add a new column to the original DataFrame that is the "rooms per household", by using the "total bedrooms" and "households" columns. Now, create a second new column for the "rooms per population" by using the "total rooms" and "population" columns, to see how many rooms each person gets on average. (2 pts). 15. Print the correlation matrix, in ascending order, of the "median hose value". (2 pts) 16. Remove the "total bedrooms column completely from the DataFrame. (2 pts) 17. Finally, remove the 4 columns you find least important to predict the "median house value" You should in total have 7 total columns left, including "median house value". (2 pts) The dataset you will use is a CSV file that contains housing data collected from the 1990 California census. You can find this dataset on Kaggle at https://www.kaggle.com/datasets/cammugent/california- housing-prices. Homework Steps The homework is out of 30 total points, all shown here below. 1. Load the dataset into a Pandas DataFrame. (1 pts) 2. Print out all the data in the first 5 and last 5 rows. (2 pts) 3. Print out the type, Non-Null count, and name of each column. (2 pts) 4. Write at least 3 of the potential dataset biases or issues you could see persisting, in a multi-line comment at the top of your program. (2 pts) 5. Print the count, mean, standard deviation, minimum, 25%, 50%, 75%, and maximum values of all the radial data. (2 pts) 6. Print out the count, unique count, mode, and frequency of the mode of the ordinal and nominal data (all have the Pandas type as object) (1 pt) 7. Plot a histogram of each numerical value in a single figure using subplots, or the hist() function in Pandas (much easier option of the two, needs just one line). (2 pt) 8. Print the mean "median house value" grouped by the "median age" in sorted order. (2 pt) 9. Plot every latitude and longitude in a scatter plot. (2 pts) 10. Using Seaborn, plot a histogram of "median house value with columns for each value of "ocean proximity". (1 pt) 11. Plot every latitude and longitude in a scatter plot, with the point weight being their value for "median house value". (1 pt) 12. Create a temporary DataFrame, and remove all rows that are not <1H Ocean". It should now be the only category remaining in this temporary DataFrame. Now, scatter plot all of these latitudes and longitudes, with the "median house value" as the point weight. (2 pts) 13. Re-using the temporary DataFrame made in the last question, apply a mask to remove any "median income values under 300,000. Plot the now masked latitude and longitudes as a scatter plot, again with point weight being the "median house value". You will no longer use the temporary DataFrame after this question. (2 pts) 14. Create and add a new column to the original DataFrame that is the "rooms per household", by using the "total bedrooms" and "households" columns. Now, create a second new column for the "rooms per population" by using the "total rooms" and "population" columns, to see how many rooms each person gets on average. (2 pts). 15. Print the correlation matrix, in ascending order, of the "median hose value". (2 pts) 16. Remove the "total bedrooms column completely from the DataFrame. (2 pts) 17. Finally, remove the 4 columns you find least important to predict the "median house value" You should in total have 7 total columns left, including "median house value". (2 pts)

Answer rating: 100% (QA)

Solution 1 Load the dataset into a Pandas DataFrame import pandas as pd data pdreadcsvcaliforniahousingpricescsv 2 Print out all the data in the first 5 and last 5 rows printdatahead printdatatail 3 P... View the full answer