from sklearn import datasets, neighbors
iris = datasets.load_iris()
model = neighbors.KNeighborsClassifier()
model.fit(iris.data, iris.target)
model.predict([7.5, 3, 6.5, 2.1])

# Take a moment to browse the official tutorials and examples

from sklearn.datasets import load_digits
digits = load_digits()
X, y = digits.data, digits.target
trainingSet = X[:-100], y[:-100]
testSet = X[-100:], y[-100:]

def evaluate_model(model):
    return model.fit(*trainingSet).score(*testSet)

from sklearn.gaussian_process import GaussianProcess
evaluate_model(GaussianProcess())

from sklearn.tree import DecisionTreeClassifier
evaluate_model(DecisionTreeClassifier())

from sklearn.svm import SVC
evaluate_model(SVC(kernel='linear', C=0.001))

from sklearn.cross_validation import cross_val_score
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression

iris = load_iris()
model = LogisticRegression()
cross_val_score(model, iris.data, iris.target)

cross_val_score(model, iris.data, iris.target, cv=4)

from sklearn.cross_validation import LeaveOneOut

cross_val_score(model, iris.data, iris.target, cv=LeaveOneOut(len(iris.target)))

from IPython.lib.display import YouTubeVideo
YouTubeVideo('1uS5b8aQ6z8')

import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import cross_val_score
from sklearn.datasets import load_digits; digits = load_digits()

model = Pipeline([
    ('pca', PCA()), 
    ('logistic', LogisticRegression()),
])
np.mean(cross_val_score(model, digits.data, digits.target))

from sklearn.preprocessing import StandardScaler

model = Pipeline([
    ('scaler', StandardScaler()),
    ('pca', PCA()), 
    ('logistic', LogisticRegression()),
])
np.mean(cross_val_score(model, digits.data, digits.target))

from sklearn.feature_extraction.text import CountVectorizer

vectorizer = CountVectorizer(min_df=1)
documents = [
    'my imagination',
    'is a piece of board',
    'my sole instrument',
    'is a wooden stick',
]
X = vectorizer.fit_transform(documents)
documentVectors = X.toarray()
documentVectors

featureNames = vectorizer.get_feature_names()
for bagOfWords in documentVectors:
    print zip(featureNames, bagOfWords)

# Adapted from 
# http://scikit-learn.org/dev/tutorial/statistical_inference/putting_together.html
from sklearn import linear_model, decomposition, datasets
from sklearn.grid_search import GridSearchCV
from sklearn.pipeline import Pipeline

pipeline = Pipeline([
    ('pca', decomposition.PCA()), 
    ('logistic', linear_model.LogisticRegression()),
])
gridSearch = GridSearchCV(pipeline, dict(
    pca__n_components=[20, 40],
    logistic__C=[1, 1000]))

digits = datasets.load_digits()
gridSearch.fit(digits.data, digits.target)
valueByParameter = gridSearch.best_estimator_.get_params()
for parameter in gridSearch.param_grid:
    print '%s: %r' % (parameter, valueByParameter[parameter])

from archiveIO import Archive, TemporaryFolder

archive = Archive('datasets/ZbigniewHerbert.tar.gz')
documents = []
categories = []
with TemporaryFolder() as temporaryFolder:
    for documentPath in archive.load(temporaryFolder):
        text = open(documentPath).read()
        documents.append(text)
        categories.append('Carpenter' in text)

from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.linear_model import SGDClassifier

pipeline = Pipeline([
    ('vect', CountVectorizer()),
    ('tfidf', TfidfTransformer()),
    ('clf', SGDClassifier()),
])

parameters = {
    'vect__max_df': (0.5, 0.75, 1.0),
    'vect__max_n': (1, 2),
    'clf__alpha': (0.00001, 0.000001),
    'clf__penalty': ('l2', 'elasticnet'),
}

from sklearn.grid_search import GridSearchCV

gridSearch = GridSearchCV(pipeline, parameters, n_jobs=-1)
gridSearch.fit(documents, categories)

valueByParameter = gridSearch.best_estimator_.get_params()
for parameter in gridSearch.param_grid:
    print '%s: %r' % (parameter, valueByParameter[parameter])
print "Best score: %0.3f" % gridSearch.best_score_

print documents[27]