def resolve():
df = loadzipdata('01', 'web_traffic.tsv', get_data_by_pd)
x = df['a']
y = df['b']
polyf = np.poly1d(np.polyfit(x, y, 10))
df['c'] = polyf(x)
df['b'].plot(style=['ro-'])
df['c'].plot(style=['bs-'])
print 'error rate {:,}'.format(np.sum((df['b'] - df['c'])**2))
sampling_factor = 15
sampling_df = df.ix[::sampling_factor]
x = sampling_df['a']
y = sampling_df['b']
polyf = np.poly1d(np.polyfit(x, y, 10))
sampling_df['c'] = polyf(x)
sampling_df['b'].plot(style=['go-'])
sampling_df['c'].plot(style=['ys-'])
print 'error rate {:,}'.format(np.sum((sampling_df['b'] - sampling_df['c'])**2))
pl.show()
def resolve():
print('===== load data =====')
df = loadzipdata('02', 'seeds.tsv', get_data_by_pd)
for i, x in enumerate(np.unique(df.X7)):
df['X7'][df.X7==x] = i
data = df[df.columns[0:7]].values
target = df.X7.values
print('===== preprocessing : selectk with SVM =====')
feats = SelectKBest()
clf = SVC()
k = [1, 2, 6, 7]
c = [0.8, 1.0, 1.2, 1.4, 1.6, 1.8, 2.0, 2.2]
degree = [1, 3, 5]
gamma= [0.0, 0.2, 2.4]
pipe = Pipeline([('feats', feats), ('svm', clf)])
estimator = GridSearchCV(pipe, dict(feats__score_func=[f_regression],
feats__k=k,
svm__degree=degree,
svm__gamma=gamma,
#svm__kernel=['rbf', 'linear'],
svm__C=c))
estimator.fit(data, target)
print(estimator.score(data, target))
print(estimator.best_estimator_)
print(estimator.best_score_)
print(estimator.best_params_)
print('===== preprocessing : pca with SVM =====')
pca = PCA()
pca.fit(data)
n_components = [2, 3, 4]
pipe = Pipeline([('pca', pca), ('svm', clf)])
estimator = GridSearchCV(pipe, dict(pca__n_components=n_components,
svm__degree=degree,
svm__gamma=gamma,
#svm__kernel=['rbf', 'linear'],
svm__C=c))
estimator.fit(data, target)
print(estimator.score(data, target))
print(estimator.best_estimator_)
print(estimator.best_score_)
print(estimator.best_params_)
print('===== preprocessing : pca with GaussianNB =====')
from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()
feats = SelectKBest()
k = [1, 2, 6, 7]
pipe = Pipeline([('feats', feats), ('gnb', clf)])
estimator = GridSearchCV(pipe, dict(feats__score_func=[f_regression],
feats__k=k,
))
estimator.fit(data, target)
print(estimator.score(data, target))
print(estimator.best_estimator_)
print(estimator.best_score_)
print(estimator.best_params_)
