- "vectorizer = HashingVectorizer(decode_error='ignore', n_features=2 ** 18,\n alternate_sign=False)\n\n\n# Iterator over parsed Reuters SGML files.\ndata_stream = stream_reuters_documents()\n\n# We learn a binary classification between the \"acq\" class and all the others.\n# \"acq\" was chosen as it is more or less evenly distributed in the Reuters\n# files. For other datasets, one should take care of creating a test set with\n# a realistic portion of positive instances.\nall_classes = np.array([0, 1])\npositive_class = 'acq'\n\n# Here are some classifiers that support the `partial_fit` method\npartial_fit_classifiers = {\n 'SGD': SGDClassifier(max_iter=5),\n 'Perceptron': Perceptron(tol=1e-3),\n 'NB Multinomial': MultinomialNB(alpha=0.01),\n 'Passive-Aggressive': PassiveAggressiveClassifier(tol=1e-3),\n}\n\n\ndef get_minibatch(doc_iter, size, pos_class=positive_class):\n \"\"\"Extract a minibatch of examples, return a tuple X_text, y.\n\n Note: size is before excluding invalid docs with no topics assigned.\n\n \"\"\"\n data = [('{title}\\n\\n{body}'.format(**doc), pos_class in doc['topics'])\n for doc in itertools.islice(doc_iter, size)\n if doc['topics']]\n if not len(data):\n return np.asarray([], dtype=int), np.asarray([], dtype=int)\n X_text, y = zip(*data)\n return X_text, np.asarray(y, dtype=int)\n\n\ndef iter_minibatches(doc_iter, minibatch_size):\n \"\"\"Generator of minibatches.\"\"\"\n X_text, y = get_minibatch(doc_iter, minibatch_size)\n while len(X_text):\n yield X_text, y\n X_text, y = get_minibatch(doc_iter, minibatch_size)\n\n\n# test data statistics\ntest_stats = {'n_test': 0, 'n_test_pos': 0}\n\n# First we hold out a number of examples to estimate accuracy\nn_test_documents = 1000\ntick = time.time()\nX_test_text, y_test = get_minibatch(data_stream, 1000)\nparsing_time = time.time() - tick\ntick = time.time()\nX_test = vectorizer.transform(X_test_text)\nvectorizing_time = time.time() - tick\ntest_stats['n_test'] += len(y_test)\ntest_stats['n_test_pos'] += sum(y_test)\nprint(\"Test set is %d documents (%d positive)\" % (len(y_test), sum(y_test)))\n\n\ndef progress(cls_name, stats):\n \"\"\"Report progress information, return a string.\"\"\"\n duration = time.time() - stats['t0']\n s = \"%20s classifier : \\t\" % cls_name\n s += \"%(n_train)6d train docs (%(n_train_pos)6d positive) \" % stats\n s += \"%(n_test)6d test docs (%(n_test_pos)6d positive) \" % test_stats\n s += \"accuracy: %(accuracy).3f \" % stats\n s += \"in %.2fs (%5d docs/s)\" % (duration, stats['n_train'] / duration)\n return s\n\n\ncls_stats = {}\n\nfor cls_name in partial_fit_classifiers:\n stats = {'n_train': 0, 'n_train_pos': 0,\n 'accuracy': 0.0, 'accuracy_history': [(0, 0)], 't0': time.time(),\n 'runtime_history': [(0, 0)], 'total_fit_time': 0.0}\n cls_stats[cls_name] = stats\n\nget_minibatch(data_stream, n_test_documents)\n# Discard test set\n\n# We will feed the classifier with mini-batches of 1000 documents; this means\n# we have at most 1000 docs in memory at any time. The smaller the document\n# batch, the bigger the relative overhead of the partial fit methods.\nminibatch_size = 1000\n\n# Create the data_stream that parses Reuters SGML files and iterates on\n# documents as a stream.\nminibatch_iterators = iter_minibatches(data_stream, minibatch_size)\ntotal_vect_time = 0.0\n\n# Main loop : iterate on mini-batches of examples\nfor i, (X_train_text, y_train) in enumerate(minibatch_iterators):\n\n tick = time.time()\n X_train = vectorizer.transform(X_train_text)\n total_vect_time += time.time() - tick\n\n for cls_name, cls in partial_fit_classifiers.items():\n tick = time.time()\n # update estimator with examples in the current mini-batch\n cls.partial_fit(X_train, y_train, classes=all_classes)\n\n # accumulate test accuracy stats\n cls_stats[cls_name]['total_fit_time'] += time.time() - tick\n cls_stats[cls_name]['n_train'] += X_train.shape[0]\n cls_stats[cls_name]['n_train_pos'] += sum(y_train)\n tick = time.time()\n cls_stats[cls_name]['accuracy'] = cls.score(X_test, y_test)\n cls_stats[cls_name]['prediction_time'] = time.time() - tick\n acc_history = (cls_stats[cls_name]['accuracy'],\n cls_stats[cls_name]['n_train'])\n cls_stats[cls_name]['accuracy_history'].append(acc_history)\n run_history = (cls_stats[cls_name]['accuracy'],\n total_vect_time + cls_stats[cls_name]['total_fit_time'])\n cls_stats[cls_name]['runtime_history'].append(run_history)\n\n if i % 3 == 0:\n print(progress(cls_name, cls_stats[cls_name]))\n if i % 3 == 0:\n print('\\n')"
0 commit comments