diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index cd8686b..d5770f0 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..69de2ac 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..09a5a2a 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..80683a0 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(): + sale_price_mean = np.mean(sale_price) + sale_price_median = np.median(sale_price) + sale_price_mode = pd.Series.mode(sale_price) + + return sale_price_mean, sale_price_median, sale_price_mode.values[0] + +calculate_statistics() + diff --git a/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc b/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc index b1b01d5..81307c9 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..9d31aa0 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..0383816 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..6c654c7 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..14d4d87 100644 --- a/q02_plot/build.py +++ b/q02_plot/build.py @@ -1,4 +1,6 @@ +# %load q02_plot/build.py # Default Imports +import numpy as np import pandas as pd import matplotlib.pyplot as plt from greyatomlib.descriptive_stats.q01_calculate_statistics.build import calculate_statistics @@ -10,3 +12,15 @@ # Draw the plot for the mean, median and mode for the dataset +def plot(): + mean = np.mean(sale_price) + median = np.median(sale_price) + mode = sale_price.mode() + plt.figure(figsize=(10,6)) + plt.hist(sale_price, bins=40) + + + 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..7d56418 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..62996d4 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..afe1f45 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..5c01941 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..bc8a404 100644 --- a/q03_pearson_correlation/build.py +++ b/q03_pearson_correlation/build.py @@ -1,9 +1,20 @@ +# %load q03_pearson_correlation/build.py # Default Imports import pandas as pd - +import numpy as np dataframe_1 = pd.read_csv('data/house_prices_multivariate.csv') dataframe_2 = pd.read_csv('data/house_prices_copy.csv') # Return the correlation value between the SalePrice column for the two loaded datasets # Your code here +def correlation(): + df1 = dataframe_1.loc[:,'SalePrice'] + df2 = dataframe_2.loc[:,'SalePrice'] + r = df1.corr(df2) + print (r) + return r +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..da5af79 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..f7e2399 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..723022f 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..15c2e9b 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..3eced64 100644 --- a/q04_spearman_correlation/build.py +++ b/q04_spearman_correlation/build.py @@ -1,8 +1,18 @@ +# %load q04_spearman_correlation/build.py # Default Import import pandas as pd - +from scipy.stats import spearmanr dataframe_1 = pd.read_csv('data/house_prices_multivariate.csv') dataframe_2 = pd.read_csv('data/house_prices_copy.csv') # Your code here +def spearman_correlation(): + df1 = dataframe_1.loc[:, 'SalePrice'] + df2 = dataframe_2.loc[:, 'SalePrice'] + corr, p_value = spearmanr(df1, df2) + print(corr) + return corr +spearman_correlation() + + diff --git a/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc index 495646a..cb5ce3b 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..6654fc0 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