diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index cd8686b..c0d6078 100644 Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_calculate_statistics/__pycache__/__init__.cpython-36.pyc b/q01_calculate_statistics/__pycache__/__init__.cpython-36.pyc index 7f99883..8717e97 100644 Binary files a/q01_calculate_statistics/__pycache__/__init__.cpython-36.pyc and b/q01_calculate_statistics/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_calculate_statistics/__pycache__/build.cpython-36.pyc b/q01_calculate_statistics/__pycache__/build.cpython-36.pyc index 58a2a31..468b650 100644 Binary files a/q01_calculate_statistics/__pycache__/build.cpython-36.pyc and b/q01_calculate_statistics/__pycache__/build.cpython-36.pyc differ diff --git a/q01_calculate_statistics/build.py b/q01_calculate_statistics/build.py index a556241..7af4882 100644 --- a/q01_calculate_statistics/build.py +++ b/q01_calculate_statistics/build.py @@ -1,11 +1,20 @@ +# %load q01_calculate_statistics/build.py # Default Imports import numpy as np import pandas as pd data = pd.read_csv('data/house_prices_multivariate.csv') -sale_price = data.loc[:, "SalePrice"] +sale_price = data.loc[:, 'SalePrice'] # Return mean,median & mode for the SalePrice Column # Write your code here +def calculate_statistics(): + mean = sale_price.mean() + median = sale_price.median() + mode = sale_price.mode()[0] + + return mean, median, mode +calculate_statistics() +sale_price.mean() diff --git a/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc b/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc index b1b01d5..9214819 100644 Binary files a/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc and b/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_calculate_statistics/tests/__pycache__/test_q01_plot.cpython-36.pyc b/q01_calculate_statistics/tests/__pycache__/test_q01_plot.cpython-36.pyc index b15e8f5..10505ca 100644 Binary files a/q01_calculate_statistics/tests/__pycache__/test_q01_plot.cpython-36.pyc and b/q01_calculate_statistics/tests/__pycache__/test_q01_plot.cpython-36.pyc differ diff --git a/q02_plot/__pycache__/__init__.cpython-36.pyc b/q02_plot/__pycache__/__init__.cpython-36.pyc index 215eac0..2db9569 100644 Binary files a/q02_plot/__pycache__/__init__.cpython-36.pyc and b/q02_plot/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_plot/__pycache__/build.cpython-36.pyc b/q02_plot/__pycache__/build.cpython-36.pyc index bed076d..23a7b58 100644 Binary files a/q02_plot/__pycache__/build.cpython-36.pyc and b/q02_plot/__pycache__/build.cpython-36.pyc differ diff --git a/q02_plot/build.py b/q02_plot/build.py index 70276d6..aba306d 100644 --- a/q02_plot/build.py +++ b/q02_plot/build.py @@ -1,3 +1,4 @@ +# %load q02_plot/build.py # Default Imports import pandas as pd import matplotlib.pyplot as plt @@ -9,4 +10,16 @@ # Draw the plot for the mean, median and mode for the dataset +def plot(): + + plt.hist(sale_price, bins = 50) + + #for plotting vertical line in figure use axvline function + plt.axvline(sale_price.mean(),color = 'r') + plt.axvline(sale_price.median(), color = 'y') + plt.axvline(sale_price.mode()[0],color= 'b') + plt.show() +plot() + + diff --git a/q02_plot/tests/__pycache__/__init__.cpython-36.pyc b/q02_plot/tests/__pycache__/__init__.cpython-36.pyc index 488a890..ee09e4e 100644 Binary files a/q02_plot/tests/__pycache__/__init__.cpython-36.pyc and b/q02_plot/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_plot/tests/__pycache__/test_q02_plot.cpython-36.pyc b/q02_plot/tests/__pycache__/test_q02_plot.cpython-36.pyc index 56f4330..be3e5fe 100644 Binary files a/q02_plot/tests/__pycache__/test_q02_plot.cpython-36.pyc and b/q02_plot/tests/__pycache__/test_q02_plot.cpython-36.pyc differ diff --git a/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc index 543c178..cc34643 100644 Binary files a/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc and b/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_pearson_correlation/__pycache__/build.cpython-36.pyc b/q03_pearson_correlation/__pycache__/build.cpython-36.pyc index ba8cf11..e13ecb1 100644 Binary files a/q03_pearson_correlation/__pycache__/build.cpython-36.pyc and b/q03_pearson_correlation/__pycache__/build.cpython-36.pyc differ diff --git a/q03_pearson_correlation/build.py b/q03_pearson_correlation/build.py index 33a762b..355a30a 100644 --- a/q03_pearson_correlation/build.py +++ b/q03_pearson_correlation/build.py @@ -1,3 +1,4 @@ +# %load q03_pearson_correlation/build.py # Default Imports import pandas as pd @@ -7,3 +8,14 @@ # Return the correlation value between the SalePrice column for the two loaded datasets # Your code here +def correlation(): + sale1 = dataframe_1['SalePrice'] + sale2 = dataframe_2['SalePrice'] + #data = pd.concat([sale1,sale2],axis = 1) + #co = data.corr() + correlation = sale1.corr(sale2) #find correlation between sale1 and sale2 + return correlation + +correlation() + + diff --git a/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc index d7eca99..ecc0965 100644 Binary files a/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc and b/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_pearson_correlation/tests/__pycache__/test_q03_correlation.cpython-36.pyc b/q03_pearson_correlation/tests/__pycache__/test_q03_correlation.cpython-36.pyc index ed900c4..aa4772c 100644 Binary files a/q03_pearson_correlation/tests/__pycache__/test_q03_correlation.cpython-36.pyc and b/q03_pearson_correlation/tests/__pycache__/test_q03_correlation.cpython-36.pyc differ diff --git a/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc index 7868267..5499663 100644 Binary files a/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc and b/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_spearman_correlation/__pycache__/build.cpython-36.pyc b/q04_spearman_correlation/__pycache__/build.cpython-36.pyc index 94f735a..5f4a53d 100644 Binary files a/q04_spearman_correlation/__pycache__/build.cpython-36.pyc and b/q04_spearman_correlation/__pycache__/build.cpython-36.pyc differ diff --git a/q04_spearman_correlation/build.py b/q04_spearman_correlation/build.py index 557be32..b63336e 100644 --- a/q04_spearman_correlation/build.py +++ b/q04_spearman_correlation/build.py @@ -1,3 +1,4 @@ +# %load q04_spearman_correlation/build.py # Default Import import pandas as pd @@ -5,4 +6,18 @@ dataframe_2 = pd.read_csv('data/house_prices_copy.csv') # Your code here +def spearman_correlation(): + sale = pd.DataFrame(dataframe_1['SalePrice']) + sale2 = pd.DataFrame(dataframe_2['SalePrice']) + sale['rank'] = sale['SalePrice'].rank() + sale2['rank2'] = sale2['SalePrice'].rank() + df = pd.concat([sale,sale2], axis = 1) + df['d'] = abs(df['rank'] - df['rank2']) + df['d squared'] = df['d'] ** 2 + s= df['d squared'].sum() + n = len(df) + result = 1- (6*s)/(n*(n**2-1)) + return result + + diff --git a/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc index 495646a..d008b44 100644 Binary files a/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc and b/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_spearman_correlation/tests/__pycache__/test_q04_spearman_correlation.cpython-36.pyc b/q04_spearman_correlation/tests/__pycache__/test_q04_spearman_correlation.cpython-36.pyc index d082652..6dde05c 100644 Binary files a/q04_spearman_correlation/tests/__pycache__/test_q04_spearman_correlation.cpython-36.pyc and b/q04_spearman_correlation/tests/__pycache__/test_q04_spearman_correlation.cpython-36.pyc differ