Improve example documentation

README.md

@@ -163,6 +163,7 @@ Full package structure can be found below:
 See **examples directory** for more demos. ["examples/knn_example.py"](https://github.com/yzhao062/Pyod/blob/master/examples/knn_example.py)
 demonstrates the basic APIs of PyOD using kNN detector. **It is noted the APIs for other detectors are similar**. 
 
+More detailed instruction of running examples can be found [here.](https://github.com/yzhao062/Pyod/blob/master/examples)
 1. Initialize a kNN detector, fit the model, and make the prediction.
     ```python
 

examples/README.md

@@ -1,19 +1,39 @@
+### How to run examples?
+
+First pyod should be installed or you should download the github respository.
+````cmd
+pip install pyod
+pip install --upgrade pyod # make sure the latest version is installed!
+````
+
+After that, you could simply copy & paste the code and run with it.
+
+### Introduction of Examples
 Examples are structured as follows:
-- Each example is structued as XXX_example.py
+- Examples are named as XXX_example.py, in whhich XXX is the model name.
+- All examples can find corresponding models at pyod/models/
 
-The implemented examples includes:
+For instance: 
 - kNN: knn_example.py
 - HBOS: hbos_example.py
 - ABOD: abod_example.py
 - ... other individual algorithms
-
 - Combination Frameworks: comb_example.py
 
+Additionally, compare_all_models.py is for comparing all implemented algorithms.
+Some examples have a Jupyter Notebook version at [Jupyter Notebooks](https://github.com/yzhao062/Pyod/tree/master/notebooks)
+
+### What if I see "xxx module could be found" or "Unresolved reference"
 Note, the examples import the models by usuing:
+
+**First check pyod is installed with pip.**
+
+If you have not but simply download the github repositoty, please make
+sure the following codes are presented at the top of the code.
+
 ```python
 import sys
 sys.path.append("..")
-
 ```
 This is a **temporary solution** for relative imports in case **pyod is not installed**.
 

examples/temp_do_not_use.py

@@ -23,13 +23,8 @@
 from pyod.utils.data import get_color_codes
 from pyod.utils.data import evaluate_print
 
-
-
 import numpy as np
 
-
-
-
 if __name__ == "__main__":
     contamination = 0.1  # percentage of outliers
     n_train = 2000  # number of training points
@@ -45,25 +40,20 @@
 
     # train CBLOF detector
     clf_name = 'CBLOF'
-#    clf = CBLOF(random_state=42)
-    clf = CBLOF(use_weights=True)
+#    clf = CBLOF(random_state=42, use_weights=True)
+    clf = CBLOF(random_state=42)
     clf.fit(X_train)
-
 
-
-
-    #
-    # # get the prediction labels and outlier scores of the training data
-    # y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
-    # y_train_scores = clf.decision_scores_  # raw outlier scores
-    #
-    # # get the prediction on the test data
-    # y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
-    # y_test_scores = clf.decision_function(X_test)  # outlier scores
-    #
-    # # evaluate and print the results
-    # print("\nOn Training Data:")
-    # evaluate_print(clf_name, y_train, y_train_scores)
-    # print("\nOn Test Data:")
-    # evaluate_print(clf_name, y_test, y_test_scores)
+    # get the prediction labels and outlier scores of the training data
+    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
+    y_train_scores = clf.decision_scores_  # raw outlier scores
+
+    # get the prediction on the test data
+    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
+    y_test_scores = clf.decision_function(X_test)  # outlier scores
 
+    # evaluate and print the results
+    print("\nOn Training Data:")
+    evaluate_print(clf_name, y_train, y_train_scores)
+    print("\nOn Test Data:")
+    evaluate_print(clf_name, y_test, y_test_scores)