### the training data (features_train, labels_train) have both "fast" and "slow" points mixed
### in together--separate them so we can give them different colors in the scatterplot,
### and visually identify them
grade_fast = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==0]
bumpy_fast = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==0]
grade_slow = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==1]
bumpy_slow = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==1]
#### initial visualization
plt.xlim(0.0, 1.0)
plt.ylim(0.0, 1.0)
plt.scatter(bumpy_fast, grade_fast, color = "b", label="fast")
plt.scatter(grade_slow, bumpy_slow, color = "r", label="slow")
plt.legend()
plt.xlabel("bumpiness")
plt.ylabel("grade")
plt.show()
# You will need to complete this function imported from the ClassifyNB script.
# Be sure to change to that code tab to complete this quiz.
clf = classify(features_train, labels_train)
accu = submitAccuracy(clf, features_test, labels_test)
print "Accuracy:", accu
### draw the decision boundary with the text points overlaid
prettyPicture(clf, features_test, labels_test)
#output_image("test.png", "png", open("test.png", "rb").read())
### in together--separate them so we can give them different colors in the scatterplot,
### and visually identify them
grade_fast = [
features_train[ii][0] for ii in range(0, len(features_train))
if labels_train[ii] == 0
]
bumpy_fast = [
features_train[ii][1] for ii in range(0, len(features_train))
if labels_train[ii] == 0
]
grade_slow = [
features_train[ii][0] for ii in range(0, len(features_train))
if labels_train[ii] == 1
]
bumpy_slow = [
features_train[ii][1] for ii in range(0, len(features_train))
if labels_train[ii] == 1
]
# You will need to complete this function imported from the ClassifyNB script.
# Be sure to change to that code tab to complete this quiz.
clf = classify(features_train, labels_train)
pred = clf.predict(features_test)
accuracy = sum(pred == labels_test) / len(pred)
# print clf.score(features_test, labels_test)
### draw the decision boundary with the text points overlaid
prettyPicture(clf, features_test, labels_test)
# output_image("test.png", "png", open("test.png", "rb").read())
#!/usr/bin/python
import pickle
from classifyNB import classify
### Task 1: Select what features you'll use.
### features_list is a list of strings, each of which is a feature name.
### The first feature must be "poi".
labels_list = ['poi']
features_list = ['poi', 'salary',
'total_payments'] # You will need to use more features
### Load the dictionary containing the dataset
data_dict = pickle.load(open("final_project_dataset.pkl", "r"))
### Task 2: Remove outliers
### Task 3: Create new feature(s)
### Store to my_dataset for easy export below.
my_dataset = data_dict
clf = classify(my_dataset, features_list)