.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/applications/plot_out_of_core_classification.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. or to run this example in your browser via Binder .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_applications_plot_out_of_core_classification.py: ====================================================== Out-of-core classification of text documents ====================================================== This is an example showing how scikit-learn can be used for classification using an out-of-core approach: learning from data that doesn't fit into main memory. We make use of an online classifier, i.e., one that supports the partial_fit method, that will be fed with batches of examples. To guarantee that the features space remains the same over time we leverage a HashingVectorizer that will project each example into the same feature space. This is especially useful in the case of text classification where new features (words) may appear in each batch. .. GENERATED FROM PYTHON SOURCE LINES 16-45 .. code-block:: Python # Authors: The scikit-learn developers # SPDX-License-Identifier: BSD-3-Clause import itertools import re import sys import tarfile import time from hashlib import sha256 from html.parser import HTMLParser from pathlib import Path from urllib.request import urlretrieve import matplotlib.pyplot as plt import numpy as np from matplotlib import rcParams from sklearn.datasets import get_data_home from sklearn.feature_extraction.text import HashingVectorizer from sklearn.linear_model import PassiveAggressiveClassifier, Perceptron, SGDClassifier from sklearn.naive_bayes import MultinomialNB def _not_in_sphinx(): # Hack to detect whether we are running by the sphinx builder return "__file__" in globals() .. GENERATED FROM PYTHON SOURCE LINES 46-52 Reuters Dataset related routines -------------------------------- The dataset used in this example is Reuters-21578 as provided by the UCI ML repository. It will be automatically downloaded and uncompressed on first run. .. GENERATED FROM PYTHON SOURCE LINES 52-187 .. code-block:: Python class ReutersParser(HTMLParser): """Utility class to parse a SGML file and yield documents one at a time.""" def __init__(self, encoding="latin-1"): HTMLParser.__init__(self) self._reset() self.encoding = encoding def handle_starttag(self, tag, attrs): method = "start_" + tag getattr(self, method, lambda x: None)(attrs) def handle_endtag(self, tag): method = "end_" + tag getattr(self, method, lambda: None)() def _reset(self): self.in_title = 0 self.in_body = 0 self.in_topics = 0 self.in_topic_d = 0 self.title = "" self.body = "" self.topics = [] self.topic_d = "" def parse(self, fd): self.docs = [] for chunk in fd: self.feed(chunk.decode(self.encoding)) for doc in self.docs: yield doc self.docs = [] self.close() def handle_data(self, data): if self.in_body: self.body += data elif self.in_title: self.title += data elif self.in_topic_d: self.topic_d += data def start_reuters(self, attributes): pass def end_reuters(self): self.body = re.sub(r"\s+", r" ", self.body) self.docs.append( {"title": self.title, "body": self.body, "topics": self.topics} ) self._reset() def start_title(self, attributes): self.in_title = 1 def end_title(self): self.in_title = 0 def start_body(self, attributes): self.in_body = 1 def end_body(self): self.in_body = 0 def start_topics(self, attributes): self.in_topics = 1 def end_topics(self): self.in_topics = 0 def start_d(self, attributes): self.in_topic_d = 1 def end_d(self): self.in_topic_d = 0 self.topics.append(self.topic_d) self.topic_d = "" def stream_reuters_documents(data_path=None): """Iterate over documents of the Reuters dataset. The Reuters archive will automatically be downloaded and uncompressed if the `data_path` directory does not exist. Documents are represented as dictionaries with 'body' (str), 'title' (str), 'topics' (list(str)) keys. """ DOWNLOAD_URL = ( "http://archive.ics.uci.edu/ml/machine-learning-databases/" "reuters21578-mld/reuters21578.tar.gz" ) ARCHIVE_SHA256 = "3bae43c9b14e387f76a61b6d82bf98a4fb5d3ef99ef7e7075ff2ccbcf59f9d30" ARCHIVE_FILENAME = "reuters21578.tar.gz" if data_path is None: data_path = Path(get_data_home()) / "reuters" else: data_path = Path(data_path) if not data_path.exists(): """Download the dataset.""" print("downloading dataset (once and for all) into %s" % data_path) data_path.mkdir(parents=True, exist_ok=True) def progress(blocknum, bs, size): total_sz_mb = "%.2f MB" % (size / 1e6) current_sz_mb = "%.2f MB" % ((blocknum * bs) / 1e6) if _not_in_sphinx(): sys.stdout.write("\rdownloaded %s / %s" % (current_sz_mb, total_sz_mb)) archive_path = data_path / ARCHIVE_FILENAME urlretrieve(DOWNLOAD_URL, filename=archive_path, reporthook=progress) if _not_in_sphinx(): sys.stdout.write("\r") # Check that the archive was not tampered: assert sha256(archive_path.read_bytes()).hexdigest() == ARCHIVE_SHA256 print("untarring Reuters dataset...") with tarfile.open(archive_path, "r:gz") as fp: fp.extractall(data_path, filter="data") print("done.") parser = ReutersParser() for filename in data_path.glob("*.sgm"): for doc in parser.parse(open(filename, "rb")): yield doc .. GENERATED FROM PYTHON SOURCE LINES 188-193 Main ---- Create the vectorizer and limit the number of features to a reasonable maximum .. GENERATED FROM PYTHON SOURCE LINES 193-329 .. code-block:: Python vectorizer = HashingVectorizer( decode_error="ignore", n_features=2**18, alternate_sign=False ) # Iterator over parsed Reuters SGML files. data_stream = stream_reuters_documents() # We learn a binary classification between the "acq" class and all the others. # "acq" was chosen as it is more or less evenly distributed in the Reuters # files. For other datasets, one should take care of creating a test set with # a realistic portion of positive instances. all_classes = np.array([0, 1]) positive_class = "acq" # Here are some classifiers that support the `partial_fit` method partial_fit_classifiers = { "SGD": SGDClassifier(max_iter=5), "Perceptron": Perceptron(), "NB Multinomial": MultinomialNB(alpha=0.01), "Passive-Aggressive": PassiveAggressiveClassifier(), } def get_minibatch(doc_iter, size, pos_class=positive_class): """Extract a minibatch of examples, return a tuple X_text, y. Note: size is before excluding invalid docs with no topics assigned. """ data = [ ("{title}\n\n{body}".format(**doc), pos_class in doc["topics"]) for doc in itertools.islice(doc_iter, size) if doc["topics"] ] if not len(data): return np.asarray([], dtype=int), np.asarray([], dtype=int) X_text, y = zip(*data) return X_text, np.asarray(y, dtype=int) def iter_minibatches(doc_iter, minibatch_size): """Generator of minibatches.""" X_text, y = get_minibatch(doc_iter, minibatch_size) while len(X_text): yield X_text, y X_text, y = get_minibatch(doc_iter, minibatch_size) # test data statistics test_stats = {"n_test": 0, "n_test_pos": 0} # First we hold out a number of examples to estimate accuracy n_test_documents = 1000 tick = time.time() X_test_text, y_test = get_minibatch(data_stream, 1000) parsing_time = time.time() - tick tick = time.time() X_test = vectorizer.transform(X_test_text) vectorizing_time = time.time() - tick test_stats["n_test"] += len(y_test) test_stats["n_test_pos"] += sum(y_test) print("Test set is %d documents (%d positive)" % (len(y_test), sum(y_test))) def progress(cls_name, stats): """Report progress information, return a string.""" duration = time.time() - stats["t0"] s = "%20s classifier : \t" % cls_name s += "%(n_train)6d train docs (%(n_train_pos)6d positive) " % stats s += "%(n_test)6d test docs (%(n_test_pos)6d positive) " % test_stats s += "accuracy: %(accuracy).3f " % stats s += "in %.2fs (%5d docs/s)" % (duration, stats["n_train"] / duration) return s cls_stats = {} for cls_name in partial_fit_classifiers: stats = { "n_train": 0, "n_train_pos": 0, "accuracy": 0.0, "accuracy_history": [(0, 0)], "t0": time.time(), "runtime_history": [(0, 0)], "total_fit_time": 0.0, } cls_stats[cls_name] = stats get_minibatch(data_stream, n_test_documents) # Discard test set # We will feed the classifier with mini-batches of 1000 documents; this means # we have at most 1000 docs in memory at any time. The smaller the document # batch, the bigger the relative overhead of the partial fit methods. minibatch_size = 1000 # Create the data_stream that parses Reuters SGML files and iterates on # documents as a stream. minibatch_iterators = iter_minibatches(data_stream, minibatch_size) total_vect_time = 0.0 # Main loop : iterate on mini-batches of examples for i, (X_train_text, y_train) in enumerate(minibatch_iterators): tick = time.time() X_train = vectorizer.transform(X_train_text) total_vect_time += time.time() - tick for cls_name, cls in partial_fit_classifiers.items(): tick = time.time() # update estimator with examples in the current mini-batch cls.partial_fit(X_train, y_train, classes=all_classes) # accumulate test accuracy stats cls_stats[cls_name]["total_fit_time"] += time.time() - tick cls_stats[cls_name]["n_train"] += X_train.shape[0] cls_stats[cls_name]["n_train_pos"] += sum(y_train) tick = time.time() cls_stats[cls_name]["accuracy"] = cls.score(X_test, y_test) cls_stats[cls_name]["prediction_time"] = time.time() - tick acc_history = (cls_stats[cls_name]["accuracy"], cls_stats[cls_name]["n_train"]) cls_stats[cls_name]["accuracy_history"].append(acc_history) run_history = ( cls_stats[cls_name]["accuracy"], total_vect_time + cls_stats[cls_name]["total_fit_time"], ) cls_stats[cls_name]["runtime_history"].append(run_history) if i % 3 == 0: print(progress(cls_name, cls_stats[cls_name])) if i % 3 == 0: print("\n") .. rst-class:: sphx-glr-script-out .. code-block:: none downloading dataset (once and for all) into /home/runner/scikit_learn_data/reuters untarring Reuters dataset... done. Test set is 982 documents (146 positive) SGD classifier : 965 train docs ( 134 positive) 982 test docs ( 146 positive) accuracy: 0.875 in 0.63s ( 1533 docs/s) Perceptron classifier : 965 train docs ( 134 positive) 982 test docs ( 146 positive) accuracy: 0.868 in 0.63s ( 1526 docs/s) NB Multinomial classifier : 965 train docs ( 134 positive) 982 test docs ( 146 positive) accuracy: 0.852 in 0.64s ( 1499 docs/s) Passive-Aggressive classifier : 965 train docs ( 134 positive) 982 test docs ( 146 positive) accuracy: 0.898 in 0.65s ( 1492 docs/s) SGD classifier : 3802 train docs ( 505 positive) 982 test docs ( 146 positive) accuracy: 0.882 in 1.82s ( 2087 docs/s) Perceptron classifier : 3802 train docs ( 505 positive) 982 test docs ( 146 positive) accuracy: 0.886 in 1.82s ( 2085 docs/s) NB Multinomial classifier : 3802 train docs ( 505 positive) 982 test docs ( 146 positive) accuracy: 0.866 in 1.83s ( 2072 docs/s) Passive-Aggressive classifier : 3802 train docs ( 505 positive) 982 test docs ( 146 positive) accuracy: 0.944 in 1.84s ( 2069 docs/s) SGD classifier : 6701 train docs ( 872 positive) 982 test docs ( 146 positive) accuracy: 0.943 in 3.00s ( 2236 docs/s) Perceptron classifier : 6701 train docs ( 872 positive) 982 test docs ( 146 positive) accuracy: 0.937 in 3.00s ( 2234 docs/s) NB Multinomial classifier : 6701 train docs ( 872 positive) 982 test docs ( 146 positive) accuracy: 0.886 in 3.01s ( 2226 docs/s) Passive-Aggressive classifier : 6701 train docs ( 872 positive) 982 test docs ( 146 positive) accuracy: 0.938 in 3.01s ( 2224 docs/s) SGD classifier : 9033 train docs ( 1062 positive) 982 test docs ( 146 positive) accuracy: 0.940 in 4.10s ( 2205 docs/s) Perceptron classifier : 9033 train docs ( 1062 positive) 982 test docs ( 146 positive) accuracy: 0.927 in 4.10s ( 2203 docs/s) NB Multinomial classifier : 9033 train docs ( 1062 positive) 982 test docs ( 146 positive) accuracy: 0.892 in 4.11s ( 2197 docs/s) Passive-Aggressive classifier : 9033 train docs ( 1062 positive) 982 test docs ( 146 positive) accuracy: 0.952 in 4.11s ( 2196 docs/s) SGD classifier : 11853 train docs ( 1371 positive) 982 test docs ( 146 positive) accuracy: 0.944 in 5.30s ( 2237 docs/s) Perceptron classifier : 11853 train docs ( 1371 positive) 982 test docs ( 146 positive) accuracy: 0.807 in 5.30s ( 2235 docs/s) NB Multinomial classifier : 11853 train docs ( 1371 positive) 982 test docs ( 146 positive) accuracy: 0.900 in 5.31s ( 2231 docs/s) Passive-Aggressive classifier : 11853 train docs ( 1371 positive) 982 test docs ( 146 positive) accuracy: 0.945 in 5.32s ( 2230 docs/s) SGD classifier : 14751 train docs ( 1771 positive) 982 test docs ( 146 positive) accuracy: 0.929 in 6.48s ( 2275 docs/s) Perceptron classifier : 14751 train docs ( 1771 positive) 982 test docs ( 146 positive) accuracy: 0.943 in 6.49s ( 2274 docs/s) NB Multinomial classifier : 14751 train docs ( 1771 positive) 982 test docs ( 146 positive) accuracy: 0.912 in 6.50s ( 2270 docs/s) Passive-Aggressive classifier : 14751 train docs ( 1771 positive) 982 test docs ( 146 positive) accuracy: 0.949 in 6.50s ( 2269 docs/s) SGD classifier : 17179 train docs ( 2071 positive) 982 test docs ( 146 positive) accuracy: 0.945 in 7.61s ( 2256 docs/s) Perceptron classifier : 17179 train docs ( 2071 positive) 982 test docs ( 146 positive) accuracy: 0.953 in 7.62s ( 2253 docs/s) NB Multinomial classifier : 17179 train docs ( 2071 positive) 982 test docs ( 146 positive) accuracy: 0.919 in 7.64s ( 2248 docs/s) Passive-Aggressive classifier : 17179 train docs ( 2071 positive) 982 test docs ( 146 positive) accuracy: 0.961 in 7.64s ( 2247 docs/s) .. GENERATED FROM PYTHON SOURCE LINES 330-339 Plot results ------------ The plot represents the learning curve of the classifier: the evolution of classification accuracy over the course of the mini-batches. Accuracy is measured on the first 1000 samples, held out as a validation set. To limit the memory consumption, we queue examples up to a fixed amount before feeding them to the learner. .. GENERATED FROM PYTHON SOURCE LINES 339-436 .. code-block:: Python def plot_accuracy(x, y, x_legend): """Plot accuracy as a function of x.""" x = np.array(x) y = np.array(y) plt.title("Classification accuracy as a function of %s" % x_legend) plt.xlabel("%s" % x_legend) plt.ylabel("Accuracy") plt.grid(True) plt.plot(x, y) rcParams["legend.fontsize"] = 10 cls_names = list(sorted(cls_stats.keys())) # Plot accuracy evolution plt.figure() for _, stats in sorted(cls_stats.items()): # Plot accuracy evolution with #examples accuracy, n_examples = zip(*stats["accuracy_history"]) plot_accuracy(n_examples, accuracy, "training examples (#)") ax = plt.gca() ax.set_ylim((0.8, 1)) plt.legend(cls_names, loc="best") plt.figure() for _, stats in sorted(cls_stats.items()): # Plot accuracy evolution with runtime accuracy, runtime = zip(*stats["runtime_history"]) plot_accuracy(runtime, accuracy, "runtime (s)") ax = plt.gca() ax.set_ylim((0.8, 1)) plt.legend(cls_names, loc="best") # Plot fitting times plt.figure() fig = plt.gcf() cls_runtime = [stats["total_fit_time"] for cls_name, stats in sorted(cls_stats.items())] cls_runtime.append(total_vect_time) cls_names.append("Vectorization") bar_colors = ["b", "g", "r", "c", "m", "y"] ax = plt.subplot(111) rectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5, color=bar_colors) ax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names))) ax.set_xticklabels(cls_names, fontsize=10) ymax = max(cls_runtime) * 1.2 ax.set_ylim((0, ymax)) ax.set_ylabel("runtime (s)") ax.set_title("Training Times") def autolabel(rectangles): """attach some text vi autolabel on rectangles.""" for rect in rectangles: height = rect.get_height() ax.text( rect.get_x() + rect.get_width() / 2.0, 1.05 * height, "%.4f" % height, ha="center", va="bottom", ) plt.setp(plt.xticks()[1], rotation=30) autolabel(rectangles) plt.tight_layout() plt.show() # Plot prediction times plt.figure() cls_runtime = [] cls_names = list(sorted(cls_stats.keys())) for cls_name, stats in sorted(cls_stats.items()): cls_runtime.append(stats["prediction_time"]) cls_runtime.append(parsing_time) cls_names.append("Read/Parse\n+Feat.Extr.") cls_runtime.append(vectorizing_time) cls_names.append("Hashing\n+Vect.") ax = plt.subplot(111) rectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5, color=bar_colors) ax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names))) ax.set_xticklabels(cls_names, fontsize=8) plt.setp(plt.xticks()[1], rotation=30) ymax = max(cls_runtime) * 1.2 ax.set_ylim((0, ymax)) ax.set_ylabel("runtime (s)") ax.set_title("Prediction Times (%d instances)" % n_test_documents) autolabel(rectangles) plt.tight_layout() plt.show() .. rst-class:: sphx-glr-horizontal * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_001.png :alt: Classification accuracy as a function of training examples (#) :srcset: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_001.png :class: sphx-glr-multi-img * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_002.png :alt: Classification accuracy as a function of runtime (s) :srcset: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_002.png :class: sphx-glr-multi-img * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_003.png :alt: Training Times :srcset: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_003.png :class: sphx-glr-multi-img * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_004.png :alt: Prediction Times (1000 instances) :srcset: /auto_examples/applications/images/sphx_glr_plot_out_of_core_classification_004.png :class: sphx-glr-multi-img .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 10.047 seconds) .. _sphx_glr_download_auto_examples_applications_plot_out_of_core_classification.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: binder-badge .. image:: images/binder_badge_logo.svg :target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/main?urlpath=lab/tree/notebooks/auto_examples/applications/plot_out_of_core_classification.ipynb :alt: Launch binder :width: 150 px .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_out_of_core_classification.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_out_of_core_classification.py ` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: plot_out_of_core_classification.zip ` .. include:: plot_out_of_core_classification.recommendations .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_