Pushing the docs to dev/ for branch: main, commit 50b818e9fbc5e2345a0610a687b89a8badeaa046

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Eustache Diemert <[email protected]>\n#          @FedericoV <https://github.com/FedericoV/>\n# License: BSD 3 clause\n\nfrom glob import glob\nimport itertools\nimport os.path\nimport re\nimport tarfile\nimport time\nimport sys\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib import rcParams\n\nfrom html.parser import HTMLParser\nfrom urllib.request import urlretrieve\nfrom sklearn.datasets import get_data_home\nfrom sklearn.feature_extraction.text import HashingVectorizer\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.linear_model import PassiveAggressiveClassifier\nfrom sklearn.linear_model import Perceptron\nfrom sklearn.naive_bayes import MultinomialNB\n\n\ndef _not_in_sphinx():\n    # Hack to detect whether we are running by the sphinx builder\n    return \"__file__\" in globals()"
+        "# Authors: Eustache Diemert <[email protected]>\n#          @FedericoV <https://github.com/FedericoV/>\n# License: BSD 3 clause\n\nimport itertools\nfrom pathlib import Path\nfrom hashlib import sha256\nimport re\nimport tarfile\nimport time\nimport sys\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib import rcParams\n\nfrom html.parser import HTMLParser\nfrom urllib.request import urlretrieve\nfrom sklearn.datasets import get_data_home\nfrom sklearn.feature_extraction.text import HashingVectorizer\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.linear_model import PassiveAggressiveClassifier\nfrom sklearn.linear_model import Perceptron\nfrom sklearn.naive_bayes import MultinomialNB\n\n\ndef _not_in_sphinx():\n    # Hack to detect whether we are running by the sphinx builder\n    return \"__file__\" in globals()"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "class ReutersParser(HTMLParser):\n    \"\"\"Utility class to parse a SGML file and yield documents one at a time.\"\"\"\n\n    def __init__(self, encoding=\"latin-1\"):\n        HTMLParser.__init__(self)\n        self._reset()\n        self.encoding = encoding\n\n    def handle_starttag(self, tag, attrs):\n        method = \"start_\" + tag\n        getattr(self, method, lambda x: None)(attrs)\n\n    def handle_endtag(self, tag):\n        method = \"end_\" + tag\n        getattr(self, method, lambda: None)()\n\n    def _reset(self):\n        self.in_title = 0\n        self.in_body = 0\n        self.in_topics = 0\n        self.in_topic_d = 0\n        self.title = \"\"\n        self.body = \"\"\n        self.topics = []\n        self.topic_d = \"\"\n\n    def parse(self, fd):\n        self.docs = []\n        for chunk in fd:\n            self.feed(chunk.decode(self.encoding))\n            for doc in self.docs:\n                yield doc\n            self.docs = []\n        self.close()\n\n    def handle_data(self, data):\n        if self.in_body:\n            self.body += data\n        elif self.in_title:\n            self.title += data\n        elif self.in_topic_d:\n            self.topic_d += data\n\n    def start_reuters(self, attributes):\n        pass\n\n    def end_reuters(self):\n        self.body = re.sub(r\"\\s+\", r\" \", self.body)\n        self.docs.append(\n            {\"title\": self.title, \"body\": self.body, \"topics\": self.topics}\n        )\n        self._reset()\n\n    def start_title(self, attributes):\n        self.in_title = 1\n\n    def end_title(self):\n        self.in_title = 0\n\n    def start_body(self, attributes):\n        self.in_body = 1\n\n    def end_body(self):\n        self.in_body = 0\n\n    def start_topics(self, attributes):\n        self.in_topics = 1\n\n    def end_topics(self):\n        self.in_topics = 0\n\n    def start_d(self, attributes):\n        self.in_topic_d = 1\n\n    def end_d(self):\n        self.in_topic_d = 0\n        self.topics.append(self.topic_d)\n        self.topic_d = \"\"\n\n\ndef stream_reuters_documents(data_path=None):\n    \"\"\"Iterate over documents of the Reuters dataset.\n\n    The Reuters archive will automatically be downloaded and uncompressed if\n    the `data_path` directory does not exist.\n\n    Documents are represented as dictionaries with 'body' (str),\n    'title' (str), 'topics' (list(str)) keys.\n\n    \"\"\"\n\n    DOWNLOAD_URL = (\n        \"http://archive.ics.uci.edu/ml/machine-learning-databases/\"\n        \"reuters21578-mld/reuters21578.tar.gz\"\n    )\n    ARCHIVE_FILENAME = \"reuters21578.tar.gz\"\n\n    if data_path is None:\n        data_path = os.path.join(get_data_home(), \"reuters\")\n    if not os.path.exists(data_path):\n        \"\"\"Download the dataset.\"\"\"\n        print(\"downloading dataset (once and for all) into %s\" % data_path)\n        os.mkdir(data_path)\n\n        def progress(blocknum, bs, size):\n            total_sz_mb = \"%.2f MB\" % (size / 1e6)\n            current_sz_mb = \"%.2f MB\" % ((blocknum * bs) / 1e6)\n            if _not_in_sphinx():\n                sys.stdout.write(\"\\rdownloaded %s / %s\" % (current_sz_mb, total_sz_mb))\n\n        archive_path = os.path.join(data_path, ARCHIVE_FILENAME)\n        urlretrieve(DOWNLOAD_URL, filename=archive_path, reporthook=progress)\n        if _not_in_sphinx():\n            sys.stdout.write(\"\\r\")\n        print(\"untarring Reuters dataset...\")\n        tarfile.open(archive_path, \"r:gz\").extractall(data_path)\n        print(\"done.\")\n\n    parser = ReutersParser()\n    for filename in glob(os.path.join(data_path, \"*.sgm\")):\n        for doc in parser.parse(open(filename, \"rb\")):\n            yield doc"
+        "class ReutersParser(HTMLParser):\n    \"\"\"Utility class to parse a SGML file and yield documents one at a time.\"\"\"\n\n    def __init__(self, encoding=\"latin-1\"):\n        HTMLParser.__init__(self)\n        self._reset()\n        self.encoding = encoding\n\n    def handle_starttag(self, tag, attrs):\n        method = \"start_\" + tag\n        getattr(self, method, lambda x: None)(attrs)\n\n    def handle_endtag(self, tag):\n        method = \"end_\" + tag\n        getattr(self, method, lambda: None)()\n\n    def _reset(self):\n        self.in_title = 0\n        self.in_body = 0\n        self.in_topics = 0\n        self.in_topic_d = 0\n        self.title = \"\"\n        self.body = \"\"\n        self.topics = []\n        self.topic_d = \"\"\n\n    def parse(self, fd):\n        self.docs = []\n        for chunk in fd:\n            self.feed(chunk.decode(self.encoding))\n            for doc in self.docs:\n                yield doc\n            self.docs = []\n        self.close()\n\n    def handle_data(self, data):\n        if self.in_body:\n            self.body += data\n        elif self.in_title:\n            self.title += data\n        elif self.in_topic_d:\n            self.topic_d += data\n\n    def start_reuters(self, attributes):\n        pass\n\n    def end_reuters(self):\n        self.body = re.sub(r\"\\s+\", r\" \", self.body)\n        self.docs.append(\n            {\"title\": self.title, \"body\": self.body, \"topics\": self.topics}\n        )\n        self._reset()\n\n    def start_title(self, attributes):\n        self.in_title = 1\n\n    def end_title(self):\n        self.in_title = 0\n\n    def start_body(self, attributes):\n        self.in_body = 1\n\n    def end_body(self):\n        self.in_body = 0\n\n    def start_topics(self, attributes):\n        self.in_topics = 1\n\n    def end_topics(self):\n        self.in_topics = 0\n\n    def start_d(self, attributes):\n        self.in_topic_d = 1\n\n    def end_d(self):\n        self.in_topic_d = 0\n        self.topics.append(self.topic_d)\n        self.topic_d = \"\"\n\n\ndef stream_reuters_documents(data_path=None):\n    \"\"\"Iterate over documents of the Reuters dataset.\n\n    The Reuters archive will automatically be downloaded and uncompressed if\n    the `data_path` directory does not exist.\n\n    Documents are represented as dictionaries with 'body' (str),\n    'title' (str), 'topics' (list(str)) keys.\n\n    \"\"\"\n\n    DOWNLOAD_URL = (\n        \"http://archive.ics.uci.edu/ml/machine-learning-databases/\"\n        \"reuters21578-mld/reuters21578.tar.gz\"\n    )\n    ARCHIVE_SHA256 = \"3bae43c9b14e387f76a61b6d82bf98a4fb5d3ef99ef7e7075ff2ccbcf59f9d30\"\n    ARCHIVE_FILENAME = \"reuters21578.tar.gz\"\n\n    if data_path is None:\n        data_path = Path(get_data_home()) / \"reuters\"\n    else:\n        data_path = Path(data_path)\n    if not data_path.exists():\n        \"\"\"Download the dataset.\"\"\"\n        print(\"downloading dataset (once and for all) into %s\" % data_path)\n        data_path.mkdir(parents=True, exist_ok=True)\n\n        def progress(blocknum, bs, size):\n            total_sz_mb = \"%.2f MB\" % (size / 1e6)\n            current_sz_mb = \"%.2f MB\" % ((blocknum * bs) / 1e6)\n            if _not_in_sphinx():\n                sys.stdout.write(\"\\rdownloaded %s / %s\" % (current_sz_mb, total_sz_mb))\n\n        archive_path = data_path / ARCHIVE_FILENAME\n\n        urlretrieve(DOWNLOAD_URL, filename=archive_path, reporthook=progress)\n        if _not_in_sphinx():\n            sys.stdout.write(\"\\r\")\n\n        # Check that the archive was not tampered:\n        assert sha256(archive_path.read_bytes()).hexdigest() == ARCHIVE_SHA256\n\n        print(\"untarring Reuters dataset...\")\n        tarfile.open(archive_path, \"r:gz\").extractall(data_path)\n        print(\"done.\")\n\n    parser = ReutersParser()\n    for filename in data_path.glob(\"*.sgm\"):\n        for doc in parser.parse(open(filename, \"rb\")):\n            yield doc"
       ]
     },
     {