Communication Exercise

import pandas as pd df = pd.read_csv( 'practice-project-dataset-1.csv' )

df.head()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15120 entries, 0 to 15119
Columns: 101 entries, Unnamed: 0 to tract_median_age_of_housing_units
dtypes: float64(31), int64(43), object(27)
memory usage: 11.7+ MB

df = df[['interest_rate','property_value','state_code','tract_minority_population_percent','derived_race','derived_sex','applicant_age']] df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15120 entries, 0 to 15119
Data columns (total 7 columns):
 #   Column                             Non-Null Count  Dtype  
---  ------                             --------------  -----  
 0   interest_rate                      10061 non-null  object 
 1   property_value                     12424 non-null  object 
 2   state_code                         14929 non-null  object 
 3   tract_minority_population_percent  15120 non-null  float64
 4   derived_race                       15120 non-null  object 
 5   derived_sex                        15120 non-null  object 
 6   applicant_age                      15120 non-null  object 
dtypes: float64(1), object(6)
memory usage: 827.0+ KB

import numpy as np df['interest_rate'] = df['interest_rate'].replace( 'Exempt', np.nan )

df['interest_rate'] = df['interest_rate'].astype( float )

df['property_value'] = df['property_value'].replace( 'Exempt', np.nan ) df['property_value'] = df['property_value'].astype( float ) df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15120 entries, 0 to 15119
Data columns (total 7 columns):
 #   Column                             Non-Null Count  Dtype  
---  ------                             --------------  -----  
 0   interest_rate                      9660 non-null   float64
 1   property_value                     12024 non-null  float64
 2   state_code                         14929 non-null  object 
 3   tract_minority_population_percent  15120 non-null  float64
 4   derived_race                       15120 non-null  object 
 5   derived_sex                        15120 non-null  object 
 6   applicant_age                      15120 non-null  object 
dtypes: float64(3), object(4)
memory usage: 827.0+ KB

df['applicant_age'].value_counts()

df['derived_race'] = df['derived_race'].astype( 'category' ) df['derived_sex'] = df['derived_sex'].astype( 'category' ) df['applicant_age'] = df['applicant_age'].astype( 'category' ) df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15120 entries, 0 to 15119
Data columns (total 7 columns):
 #   Column                             Non-Null Count  Dtype   
---  ------                             --------------  -----   
 0   interest_rate                      9660 non-null   float64 
 1   property_value                     12024 non-null  float64 
 2   state_code                         14929 non-null  object  
 3   tract_minority_population_percent  15120 non-null  float64 
 4   derived_race                       15120 non-null  category
 5   derived_sex                        15120 non-null  category
 6   applicant_age                      15120 non-null  category
dtypes: category(3), float64(3), object(1)
memory usage: 517.9+ KB

# Create two new DataFrames derived from "df", filtered based upon minority # population percentage lower_prices = df[df['property_value'] < 500000] high_minority = lower_prices[lower_prices['tract_minority_population_percent'] > 75] low_minority = lower_prices[lower_prices['tract_minority_population_percent'] < 25] # The dataframes high_minority and low_minority were created for graphing purposes # as filtered DataFrames to compare property values in high- and low-minority areas

# Plot the derived DataFrames as a histogram for juxtaposition import matplotlib.pyplot as plt plt.hist( [ high_minority['property_value'], low_minority['property_value'] ], bins=20, density=True ) plt.legend( [ 'High % minority', 'Low % minority' ] ) plt.title( 'Sample of 2018 Home Mortgage Applications' ) plt.xlabel( 'Property Value' ) plt.ylabel( 'Proportion' ) plt.show() # A histogram was constructed using 20 points of reference to compare the # property values of areas with high and low percentages of minority residents

# Construct a calculation to formulate the confidence interval of the data high_minority['property_value'].mean(), low_minority['property_value'].mean() # The high and low minority DataFrames were averaged in order to compare the # statistical average property value to rudimentally evaluate price difference

# Test the null hypothesis utilizing a 5% confidence level from scipy import stats alpha = 0.05 statistic, pvalue = stats.ttest_ind( high_minority['property_value'], low_minority['property_value'], equal_var=False ) pvalue < alpha # reject H_0? # The high_minority and low_minority DataFrames are used to conduct a T-Test to test # H_0, that the mean property value is constant regardless of minority population