Merge pull request #12 from julianspaeth/update-rsf

Fix smaller bugs

CITATION.cff

@@ -6,4 +6,4 @@ authors:
     orcid: https://orcid.org/0000-0003-4562-5816
 title: Random Survival Forest
 doi: 10.5281/zenodo.5146376
-version: v0.1.1-beta
+version: v0.1.2-beta

README.md

@@ -21,23 +21,24 @@ $ pip install random-survival-forest
 ## Getting Started
 
 ```python
->>> from random_survival_forest import RandomSurvivalForest, concordance_index
->>> from lifelines import datasets
->>> from sklearn.model_selection import train_test_split
+from random_survival_forest.models import RandomSurvivalForest
+from random_survival_forest.scoring import concordance_index
+from lifelines import datasets
+from sklearn.model_selection import train_test_split
 
 
->>> rossi = datasets.load_rossi()
+rossi = datasets.load_rossi()
 # Attention: duration column must be index 0, event column index 1 in y
->>> y = rossi.loc[:, ["week", "arrest"]]
->>> X = rossi.drop(["arrest", "week"], axis=1)
->>> X, X_test, y, y_test = train_test_split(X, y, test_size=0.25)
+y = rossi.loc[:, ["week", "arrest"]]
+X = rossi.drop(["arrest", "week"], axis=1)
+X, X_test, y, y_test = train_test_split(X, y, test_size=0.25)
 
 
->>> rsf = RandomSurvivalForest(n_estimators=20, n_jobs=-1)
->>> rsf = rsf.fit(X, y)
->>> y_pred = rsf.predict(X_test)
->>> c_val = concordance_index(y_time=y_test["week"], y_pred=y_pred, y_event=y_test["arrest"])
->>> print("C-index", round(c_val, 3))
+rsf = RandomSurvivalForest(n_estimators=20, n_jobs=-1)
+rsf = rsf.fit(X, y)
+y_pred = rsf.predict(X_test)
+c_val = concordance_index(y_time=y_test["week"], y_pred=y_pred, y_event=y_test["arrest"])
+print("C-index", round(c_val, 3))
 ```
 
 ## Feedback

build.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+rm -r random_survival_forest.egg-info
+rm -r build
+rm -r dist
+python -m pip install --user --upgrade setuptools wheel
+python -m pip install --user --upgrade twine
+python setup.py sdist bdist_wheel
+python -m twine upload dist/*

example.py

@@ -1,19 +1,22 @@
-from random_survival_forest import RandomSurvivalForest, concordance_index
+import time
+
 from lifelines import datasets
 from sklearn.model_selection import train_test_split
-import time
+
+from random_survival_forest.models import RandomSurvivalForest
+from random_survival_forest.scoring import concordance_index
 
 rossi = datasets.load_rossi()
 # Attention: duration column must be index 0, event column index 1 in y
 y = rossi.loc[:, ["arrest", "week"]]
 X = rossi.drop(["arrest", "week"], axis=1)
-X, X_test, y, y_test = train_test_split(X, y, test_size=0.25, random_state=10)
+X, X_test, y, y_test = train_test_split(X, y, test_size=0.33, random_state=10)
 
-print("RSF")
+print("Start training...")
 start_time = time.time()
-rsf = RandomSurvivalForest(n_estimators=20, n_jobs=-1, min_leaf=10)
+rsf = RandomSurvivalForest(n_estimators=10, n_jobs=-1, random_state=10)
 rsf = rsf.fit(X, y)
-print("--- %s seconds ---" % (time.time() - start_time))
+print(f'--- {round(time.time() - start_time, 3)} seconds ---')
 y_pred = rsf.predict(X_test)
 c_val = concordance_index(y_time=y_test["week"], y_pred=y_pred, y_event=y_test["arrest"])
-print("C-index", round(c_val, 3))
+print(f'C-index {round(c_val, 3)}')