Update load_boston in README.md (#340)

* Update load_boston in README.md

* Remove load_boston in regression.py

* Remove load_boston in survival.py

* Add import in regression.py

* Add import in survival.py

* Add pandas in pyproject.toml

* Remove pandas from pyproject.toml

* black format

* make lint

README.md

@@ -32,11 +32,15 @@ Probabilistic regression example on the Boston housing dataset:
 ```python
 from ngboost import NGBRegressor
 
-from sklearn.datasets import load_boston
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import mean_squared_error
 
-X, Y = load_boston(True)
+#Load Boston housing dataset
+data_url = "http://lib.stat.cmu.edu/datasets/boston"
+raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+Y = raw_df.values[1::2, 2]
+
 X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
 ngb = NGBRegressor().fit(X_train, Y_train)

examples/regression.py

@@ -1,13 +1,18 @@
-from sklearn.datasets import load_boston
+import numpy as np
+import pandas as pd
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import train_test_split
 
 from ngboost import NGBRegressor
 from ngboost.distns import Normal
 
 if __name__ == "__main__":
+    # Load Boston housing dataset
+    data_url = "http://lib.stat.cmu.edu/datasets/boston"
+    raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+    X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+    Y = raw_df.values[1::2, 2]
 
-    X, Y = load_boston(return_X_y=True)
     X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
     ngb = NGBRegressor(Dist=Normal).fit(X_train, Y_train)

examples/survival.py

@@ -1,14 +1,18 @@
 import numpy as np
-from sklearn.datasets import load_boston
+import pandas as pd
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import train_test_split
 
 from ngboost import NGBSurvival
 from ngboost.distns import LogNormal
 
 if __name__ == "__main__":
+    # Load Boston housing dataset
+    data_url = "http://lib.stat.cmu.edu/datasets/boston"
+    raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+    X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+    Y = raw_df.values[1::2, 2]
 
-    X, Y = load_boston(return_X_y=True)
     X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
     # introduce administrative censoring