diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index f93420f..5a47ce6 100644 Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc index 29d3927..0cb8ea9 100644 Binary files a/q01_load_data/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc index ef1e203..053bc3c 100644 Binary files a/q01_load_data/__pycache__/build.cpython-36.pyc and b/q01_load_data/__pycache__/build.cpython-36.pyc differ diff --git a/q01_load_data/build.py b/q01_load_data/build.py index 1fea6ca..850af4a 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,8 +1,16 @@ +# %load q01_load_data/build.py # Default imports import pandas as pd path = 'data/house_prices_multivariate.csv' -# Write your code here : +def load_data(path): + df=pd.read_csv(path,index_col = False) + return df + +load_data(path) +x=2 +x + diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index b882452..907a70a 100644 Binary files a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc b/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc index 736de76..3e249c5 100644 Binary files a/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc and b/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc differ diff --git a/q02_data_splitter/__pycache__/__init__.cpython-36.pyc b/q02_data_splitter/__pycache__/__init__.cpython-36.pyc index 67f0b61..d647bed 100644 Binary files a/q02_data_splitter/__pycache__/__init__.cpython-36.pyc and b/q02_data_splitter/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_data_splitter/__pycache__/build.cpython-36.pyc b/q02_data_splitter/__pycache__/build.cpython-36.pyc index 412515b..cf04570 100644 Binary files a/q02_data_splitter/__pycache__/build.cpython-36.pyc and b/q02_data_splitter/__pycache__/build.cpython-36.pyc differ diff --git a/q02_data_splitter/build.py b/q02_data_splitter/build.py index cf517fe..d2f33d0 100644 --- a/q02_data_splitter/build.py +++ b/q02_data_splitter/build.py @@ -1,8 +1,13 @@ +# %load q02_data_splitter/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data import pandas as pd df = load_data('data/house_prices_multivariate.csv') +def data_splitter(df): + df=df + X = df.iloc[:,:-1] + y = df.SalePrice + return X,y +data_splitter(df) -# Your Code Here - diff --git a/q02_data_splitter/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_splitter/tests/__pycache__/__init__.cpython-36.pyc index e7e9527..1c6c34a 100644 Binary files a/q02_data_splitter/tests/__pycache__/__init__.cpython-36.pyc and b/q02_data_splitter/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_data_splitter/tests/__pycache__/test_q02_data_splitter.cpython-36.pyc b/q02_data_splitter/tests/__pycache__/test_q02_data_splitter.cpython-36.pyc index db949a7..6df8c92 100644 Binary files a/q02_data_splitter/tests/__pycache__/test_q02_data_splitter.cpython-36.pyc and b/q02_data_splitter/tests/__pycache__/test_q02_data_splitter.cpython-36.pyc differ diff --git a/q03_linear_regression/__pycache__/__init__.cpython-36.pyc b/q03_linear_regression/__pycache__/__init__.cpython-36.pyc index b8f4cc0..2e5f1aa 100644 Binary files a/q03_linear_regression/__pycache__/__init__.cpython-36.pyc and b/q03_linear_regression/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_linear_regression/__pycache__/build.cpython-36.pyc b/q03_linear_regression/__pycache__/build.cpython-36.pyc index d3a347e..8f6b3aa 100644 Binary files a/q03_linear_regression/__pycache__/build.cpython-36.pyc and b/q03_linear_regression/__pycache__/build.cpython-36.pyc differ diff --git a/q03_linear_regression/build.py b/q03_linear_regression/build.py index 03ab5ff..eb1cf52 100644 --- a/q03_linear_regression/build.py +++ b/q03_linear_regression/build.py @@ -1,3 +1,4 @@ +# %load q03_linear_regression/build.py from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter from sklearn.linear_model import LinearRegression @@ -7,4 +8,12 @@ # Write your code here : +def linear_regression(X,y): + regressor = LinearRegression() + linearModel=regressor.fit(X, y) + return linearModel + +linear_regression(X,y) + + diff --git a/q03_linear_regression/tests/__pycache__/__init__.cpython-36.pyc b/q03_linear_regression/tests/__pycache__/__init__.cpython-36.pyc index 739e010..b4fc559 100644 Binary files a/q03_linear_regression/tests/__pycache__/__init__.cpython-36.pyc and b/q03_linear_regression/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_linear_regression/tests/__pycache__/test_q03_linear_regression.cpython-36.pyc b/q03_linear_regression/tests/__pycache__/test_q03_linear_regression.cpython-36.pyc index fe5fba5..f73ee8d 100644 Binary files a/q03_linear_regression/tests/__pycache__/test_q03_linear_regression.cpython-36.pyc and b/q03_linear_regression/tests/__pycache__/test_q03_linear_regression.cpython-36.pyc differ diff --git a/q04_linear_predictor/__pycache__/__init__.cpython-36.pyc b/q04_linear_predictor/__pycache__/__init__.cpython-36.pyc index 3c623bd..14f8c97 100644 Binary files a/q04_linear_predictor/__pycache__/__init__.cpython-36.pyc and b/q04_linear_predictor/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_linear_predictor/__pycache__/build.cpython-36.pyc b/q04_linear_predictor/__pycache__/build.cpython-36.pyc index 2e68f8e..52bcde7 100644 Binary files a/q04_linear_predictor/__pycache__/build.cpython-36.pyc and b/q04_linear_predictor/__pycache__/build.cpython-36.pyc differ diff --git a/q04_linear_predictor/build.py b/q04_linear_predictor/build.py index e3c8357..81f67d4 100644 --- a/q04_linear_predictor/build.py +++ b/q04_linear_predictor/build.py @@ -1,3 +1,4 @@ +# %load q04_linear_predictor/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter @@ -10,5 +11,11 @@ X, y = data_splitter(dataframe) linear_model = linear_regression(X, y) +def linear_predictor(linear_model,X,y): + y_pred = linear_model.predict(X) + mean_square_err=mean_squared_error(y_pred, y) + mean_abs_err=mean_absolute_error(y_pred,y) + r_sqr=r2_score(y,y_pred) + return y_pred,mean_square_err,mean_abs_err,r_sqr + -# Your code here diff --git a/q04_linear_predictor/tests/__pycache__/__init__.cpython-36.pyc b/q04_linear_predictor/tests/__pycache__/__init__.cpython-36.pyc index 8abd4d2..425cb35 100644 Binary files a/q04_linear_predictor/tests/__pycache__/__init__.cpython-36.pyc and b/q04_linear_predictor/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_linear_predictor/tests/__pycache__/test_q04_linear_predictor.cpython-36.pyc b/q04_linear_predictor/tests/__pycache__/test_q04_linear_predictor.cpython-36.pyc index 7b2e751..22ea4d9 100644 Binary files a/q04_linear_predictor/tests/__pycache__/test_q04_linear_predictor.cpython-36.pyc and b/q04_linear_predictor/tests/__pycache__/test_q04_linear_predictor.cpython-36.pyc differ diff --git a/q05_residuals/__pycache__/__init__.cpython-36.pyc b/q05_residuals/__pycache__/__init__.cpython-36.pyc index 82a3d44..47d4e2e 100644 Binary files a/q05_residuals/__pycache__/__init__.cpython-36.pyc and b/q05_residuals/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_residuals/__pycache__/build.cpython-36.pyc b/q05_residuals/__pycache__/build.cpython-36.pyc index 73e9d89..4f02f05 100644 Binary files a/q05_residuals/__pycache__/build.cpython-36.pyc and b/q05_residuals/__pycache__/build.cpython-36.pyc differ diff --git a/q05_residuals/build.py b/q05_residuals/build.py index aaef679..bc215e7 100644 --- a/q05_residuals/build.py +++ b/q05_residuals/build.py @@ -1,3 +1,4 @@ +# %load q05_residuals/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter @@ -10,5 +11,8 @@ linear_model = linear_regression(X, y) y_pred, _, __, ___ = linear_predictor(linear_model, X, y) +def residuals(y,y_pred): + error_residuals=y-y_pred + return error_residuals + -# Your code here diff --git a/q05_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q05_residuals/tests/__pycache__/__init__.cpython-36.pyc index 95e65cc..5283a9f 100644 Binary files a/q05_residuals/tests/__pycache__/__init__.cpython-36.pyc and b/q05_residuals/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_residuals/tests/__pycache__/test_q05_residuals.cpython-36.pyc b/q05_residuals/tests/__pycache__/test_q05_residuals.cpython-36.pyc index 4263cb0..18bb077 100644 Binary files a/q05_residuals/tests/__pycache__/test_q05_residuals.cpython-36.pyc and b/q05_residuals/tests/__pycache__/test_q05_residuals.cpython-36.pyc differ diff --git a/q06_plot_residuals/__pycache__/__init__.cpython-36.pyc b/q06_plot_residuals/__pycache__/__init__.cpython-36.pyc index cbab384..4579887 100644 Binary files a/q06_plot_residuals/__pycache__/__init__.cpython-36.pyc and b/q06_plot_residuals/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_plot_residuals/__pycache__/build.cpython-36.pyc b/q06_plot_residuals/__pycache__/build.cpython-36.pyc index 67ae5f6..ae5d3cb 100644 Binary files a/q06_plot_residuals/__pycache__/build.cpython-36.pyc and b/q06_plot_residuals/__pycache__/build.cpython-36.pyc differ diff --git a/q06_plot_residuals/build.py b/q06_plot_residuals/build.py index cfd3722..731f1a4 100644 --- a/q06_plot_residuals/build.py +++ b/q06_plot_residuals/build.py @@ -1,3 +1,4 @@ +# %load q06_plot_residuals/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter @@ -15,5 +16,12 @@ error_residuals = residuals(y, y_pred) -# Your code here +def plot_residuals(y,error_residuals): + plt.scatter(y,error_residuals) + plt.xlabel('Sale Price') + plt.ylabel('Error') + plt.title('Residual plot') + plt.show(); + + diff --git a/q06_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q06_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc index 3ce3f60..d53a883 100644 Binary files a/q06_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc and b/q06_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_plot_residuals/tests/__pycache__/test_q06_plot_residuals.cpython-36.pyc b/q06_plot_residuals/tests/__pycache__/test_q06_plot_residuals.cpython-36.pyc index 5f787c4..0e9e5e3 100644 Binary files a/q06_plot_residuals/tests/__pycache__/test_q06_plot_residuals.cpython-36.pyc and b/q06_plot_residuals/tests/__pycache__/test_q06_plot_residuals.cpython-36.pyc differ diff --git a/q07_hist_residuals/__pycache__/__init__.cpython-36.pyc b/q07_hist_residuals/__pycache__/__init__.cpython-36.pyc index 4823574..163a4af 100644 Binary files a/q07_hist_residuals/__pycache__/__init__.cpython-36.pyc and b/q07_hist_residuals/__pycache__/__init__.cpython-36.pyc differ diff --git a/q07_hist_residuals/__pycache__/build.cpython-36.pyc b/q07_hist_residuals/__pycache__/build.cpython-36.pyc index e030b2b..2e16eb0 100644 Binary files a/q07_hist_residuals/__pycache__/build.cpython-36.pyc and b/q07_hist_residuals/__pycache__/build.cpython-36.pyc differ diff --git a/q07_hist_residuals/build.py b/q07_hist_residuals/build.py index 2f999aa..d353949 100644 --- a/q07_hist_residuals/build.py +++ b/q07_hist_residuals/build.py @@ -1,3 +1,4 @@ +# %load q07_hist_residuals/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter @@ -19,3 +20,7 @@ def hist_residuals(error_residuals, bins=60): plt.figure(figsize=(15,8)) plt.hist(error_residuals, bins=bins) + plt.show(); + + + diff --git a/q07_hist_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q07_hist_residuals/tests/__pycache__/__init__.cpython-36.pyc index f7acf95..68a7d56 100644 Binary files a/q07_hist_residuals/tests/__pycache__/__init__.cpython-36.pyc and b/q07_hist_residuals/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q07_hist_residuals/tests/__pycache__/test_q07_hist_residuals.cpython-36.pyc b/q07_hist_residuals/tests/__pycache__/test_q07_hist_residuals.cpython-36.pyc index 3919c93..e61f5e8 100644 Binary files a/q07_hist_residuals/tests/__pycache__/test_q07_hist_residuals.cpython-36.pyc and b/q07_hist_residuals/tests/__pycache__/test_q07_hist_residuals.cpython-36.pyc differ diff --git a/q08_qq_residuals/__pycache__/__init__.cpython-36.pyc b/q08_qq_residuals/__pycache__/__init__.cpython-36.pyc index 8069022..0cfb949 100644 Binary files a/q08_qq_residuals/__pycache__/__init__.cpython-36.pyc and b/q08_qq_residuals/__pycache__/__init__.cpython-36.pyc differ diff --git a/q08_qq_residuals/__pycache__/build.cpython-36.pyc b/q08_qq_residuals/__pycache__/build.cpython-36.pyc index d42be94..f0c6571 100644 Binary files a/q08_qq_residuals/__pycache__/build.cpython-36.pyc and b/q08_qq_residuals/__pycache__/build.cpython-36.pyc differ diff --git a/q08_qq_residuals/build.py b/q08_qq_residuals/build.py index bb05f08..5bd8649 100644 --- a/q08_qq_residuals/build.py +++ b/q08_qq_residuals/build.py @@ -1,3 +1,4 @@ +# %load q08_qq_residuals/build.py # Default Imports from greyatomlib.linear_regression.q01_load_data.build import load_data from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter @@ -6,6 +7,7 @@ from greyatomlib.linear_regression.q05_residuals.build import residuals from sklearn.linear_model import LinearRegression import matplotlib.pyplot as plt +import scipy.stats as stats plt.switch_backend('agg') import pylab @@ -18,5 +20,8 @@ y_pred, _, __, ___ = linear_predictor(linear_model, X, y) error_residuals = residuals(y, y_pred) +def qq_residuals(error_residuals): + stats.probplot(error_residuals, dist='norm', plot=pylab) + pylab.show() + -# Your code here diff --git a/q08_qq_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q08_qq_residuals/tests/__pycache__/__init__.cpython-36.pyc index 320d34e..9cda935 100644 Binary files a/q08_qq_residuals/tests/__pycache__/__init__.cpython-36.pyc and b/q08_qq_residuals/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q08_qq_residuals/tests/__pycache__/test_q08_qq_residuals.cpython-36.pyc b/q08_qq_residuals/tests/__pycache__/test_q08_qq_residuals.cpython-36.pyc index bc94040..0f8c380 100644 Binary files a/q08_qq_residuals/tests/__pycache__/test_q08_qq_residuals.cpython-36.pyc and b/q08_qq_residuals/tests/__pycache__/test_q08_qq_residuals.cpython-36.pyc differ