intent_svm.py

import numpy as np
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.cross_validation import train_test_split

from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report

import matplotlib.pyplot as plt
import pickle

samples = np.loadtxt('vectors.dat')

X=samples

labels_text = [ l.strip() for l in open('labels.dat').readlines()]
label_index = list(set(labels_text))
print(label_index)
n = len(labels_text)
labels = np.array([label_index.index(l) for l in labels_text]).astype('int64')

tuned_parameters = [
  {'C': [1,2,5, 10,20, 100], 'kernel': ['linear']}
  #{'C': [1, 10, 100, 1000], 'gamma': [0.001, 0.0001], 'kernel': ['rbf']},
 ]

X_train, X_test, y_train, y_test = train_test_split(
    X, labels, test_size=0.1, random_state=0)

scores = ['precision']

for score in scores:
    print("# Tuning hyper-parameters for %s" % score)
    print()

    clf = GridSearchCV(SVC(C=1), tuned_parameters, cv=3,
                       scoring='%s_weighted' % score)
    clf.fit(X_train, y_train)
    
    print("Best parameters set found on development set:")
    print()
    print(clf.best_params_)
    print()
    print("Grid scores on development set:")
    print()
    for params, mean_score, scores in clf.grid_scores_:
        print("%0.3f (+/-%0.03f) for %r"
              % (mean_score, scores.std() * 2, params))
    print()

    print("Detailed classification report:")
    print()
    print("The model is trained on the full development set.")
    print("The scores are computed on the full evaluation set.")
    print()
    y_true, y_pred = y_test, clf.predict(X_test)
    print(classification_report(y_true, y_pred))
    print()

sentences = open('sentences.dat').readlines()
idx=np.random.choice(n, 10)
for i in range(10):
    label_pred = clf.predict(samples[i,:].reshape(1, -1))
    
    print("ut : {0} label {1} predict {2}".format(sentences[i].strip(),labels_text[i],label_index[label_pred]))