Scikit-learn

sudo pip install -U scikit-learn
Password:
The directory '/Users/jingruijiaoyu/Library/Caches/pip/http' or its parent directory is not owned by the current user and the cache has been disabled. Please check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.
The directory '/Users/jingruijiaoyu/Library/Caches/pip' or its parent directory is not owned by the current user and caching wheels has been disabled. check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.
Collecting scikit-learn
Downloading scikit_learn-0.18.1-cp27-cp27m-macosx_10_6_intel.macosx_10_9_intel.macosx_10_9_x86_64.macosx_10_10_intel.macosx_10_10_x86_64.whl (7.5MB)
100% |████████████████████████████████| 7.5MB 47kB/s 
Installing collected packages: scikit-learn
Successfully installed scikit-learn-0.18.1

>>> import numpy as np 
>>> import urllib
>>> url = "http://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data"
>>> raw_data = urllib.urlopen(url)
>>> dataset = np.loadtxt(raw_data,delimiter=",")
>>> X = dataset[:,0:7]
>>> y = dataset[:,8]
>>> from sklearn import preprocessing
>>> scaled_X = preprocessing.scale(X)
>>> normalized_X = preprocessing.normalize(X)
>>> standardized_X = preprocessing.scale(X))
File "<stdin>", line 1
standardized_X = preprocessing.scale(X))
^
SyntaxError: invalid syntax
>>> standardized_X = preprocessing.scale(X)
>>> from sklearn import metrics 
>>> from sklearn.ensemble import ExtraTreesClassifier
>>> model = ExtraTreesClassifier()
>>> model.fit(X,y)
ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',
max_depth=None, max_features='auto', max_leaf_nodes=None,
min_impurity_split=1e-07, min_samples_leaf=1,
min_samples_split=2, min_weight_fraction_leaf=0.0,
n_estimators=10, n_jobs=1, oob_score=False, random_state=None,
verbose=0, warm_start=False)
>>> print(model.feature_importances)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'ExtraTreesClassifier' object has no attribute 'feature_importances'
>>> print(model.feature_importances_)
[ 0.1318342   0.26854907  0.12795734  0.08771382  0.08287976  0.15588338
0.14518245]
>>> from sklearn import metrics
>>> from sklearn.linear_model import LogisticRegression
>>> model = LogisticRegression()
>>> model.fit(X,y)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
verbose=0, warm_start=False)
>>> print('MODEL')
MODEL
>>> print(model)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
verbose=0, warm_start=False)
>>> expected = y
>>> predicted = model.predict(X)
>>> print('RESULT')
RESULT
>>> print(metrics.classificaction_report(expected,predicted))
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'module' object has no attribute 'classificaction_report'
>>> print(metrics.classification_report(expected,predicted))
precision    recall  f1-score   support

0.0       0.79      0.89      0.84       500
1.0       0.74      0.55      0.63       268

avg / total       0.77      0.77      0.77       768

>>> print('CONFUSION MATRIX')
CONFUSION MATRIX
>>> print(metrics.confusion_matrix(expected,predicted))
[[447  53]
[120 148]]
>>> from sklearn import metrics
>>> from sklearn.naive_bayes import GaussianNB
>>> model = GaussianNB()
>>> model.fit(X,y)
GaussianNB(priors=None)
>>> print('MODEL')
MODEL
>>> print(model)
GaussianNB(priors=None)
>>> expected = y
>>> print('RESULT')
RESULT
>>> print(metrics.classification_report(expected,predicted))
precision    recall  f1-score   support

0.0       0.79      0.89      0.84       500
1.0       0.74      0.55      0.63       268

avg / total       0.77      0.77      0.77       768

>>> print('CONFUSION MATRIX')
CONFUSION MATRIX
>>> print(metrics.confusion_matrix(expected,predicted))
[[447  53]
[120 148]]
>>>