{ "cells": [ { "cell_type": "markdown", "id": "17fe0531-3a80-41b8-8f4c-bfd8f0799175", "metadata": {}, "source": [ "# 12 - Movie reviews classification" ] }, { "cell_type": "code", "execution_count": 1, "id": "1be8ec85-a6e8-4786-b9fd-3fbffcd58cc8", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 6, "id": "2e35e069-46f7-4d8f-b0f5-dd16dd97b1be", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "

	label	review
0	neg	how do films like mouse hunt get into theatres...
1	neg	some talented actresses are blessed with a dem...
2	pos	this has been an extraordinary year for austra...
3	pos	according to hollywood movies made in last few...
4	neg	my first press screening of 1998 and already i...

\n", "

" ], "text/plain": [ " label review\n", "0 neg how do films like mouse hunt get into theatres...\n", "1 neg some talented actresses are blessed with a dem...\n", "2 pos this has been an extraordinary year for austra...\n", "3 pos according to hollywood movies made in last few...\n", "4 neg my first press screening of 1998 and already i..." ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_table('moviereviews.tsv')\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 7, "id": "46dbc114-3fb8-49af-b895-95e926ed29e0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2000" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(df)" ] }, { "cell_type": "code", "execution_count": 11, "id": "087311b5-2f7b-4d7e-af76-ab9b88d7b65c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "how do films like mouse hunt get into theatres ? \n", "isn't there a law or something ? \n", "this diabolical load of claptrap from steven speilberg's dreamworks studio is hollywood family fare at its deadly worst . \n", "mouse hunt takes the bare threads of a plot and tries to prop it up with overacting and flat-out stupid slapstick that makes comedies like jingle all the way look decent by comparison . \n", "writer adam rifkin and director gore verbinski are the names chiefly responsible for this swill . \n", "the plot , for what its worth , concerns two brothers ( nathan lane and an appalling lee evens ) who inherit a poorly run string factory and a seemingly worthless house from their eccentric father . \n", "deciding to check out the long-abandoned house , they soon learn that it's worth a fortune and set about selling it in auction to the highest bidder . \n", "but battling them at every turn is a very smart mouse , happy with his run-down little abode and wanting it to stay that way . \n", "the story alternates between unfunny scenes of the brothers bickering over what to do with their inheritance and endless action sequences as the two take on their increasingly determined furry foe . \n", "whatever promise the film starts with soon deteriorates into boring dialogue , terrible overacting , and increasingly uninspired slapstick that becomes all sound and fury , signifying nothing . \n", "the script becomes so unspeakably bad that the best line poor lee evens can utter after another run in with the rodent is : \" i hate that mouse \" . \n", "oh cringe ! \n", "this is home alone all over again , and ten times worse . \n", "one touching scene early on is worth mentioning . \n", "we follow the mouse through a maze of walls and pipes until he arrives at his makeshift abode somewhere in a wall . \n", "he jumps into a tiny bed , pulls up a makeshift sheet and snuggles up to sleep , seemingly happy and just wanting to be left alone . \n", "it's a magical little moment in an otherwise soulless film . \n", "a message to speilberg : if you want dreamworks to be associated with some kind of artistic credibility , then either give all concerned in mouse hunt a swift kick up the arse or hire yourself some decent writers and directors . \n", "this kind of rubbish will just not do at all . \n", "\n" ] } ], "source": [ "print(df['review'][0])" ] }, { "cell_type": "code", "execution_count": 12, "id": "8f2f154b-764c-4f6e-b5f6-18939cfc2599", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "label 0\n", "review 35\n", "dtype: int64" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 13, "id": "ba06064d-0b34-421a-8cc4-89d968315091", "metadata": {}, "outputs": [], "source": [ "df.dropna(inplace=True)" ] }, { "cell_type": "code", "execution_count": 14, "id": "e285086a-5bbf-4308-b285-456b90d10e3e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "label 0\n", "review 0\n", "dtype: int64" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 19, "id": "c2f5c47b-06cd-4f61-adff-c8c09c0e12d2", "metadata": {}, "outputs": [], "source": [ "blanks = []\n", "\n", "# (index, label, review text)\n", "for i,lb,rv in df.itertuples():\n", " if (rv.isspace()):\n", " blanks.append(i)\n", " " ] }, { "cell_type": "code", "execution_count": 20, "id": "a3d8a06c-bd92-4dab-8ed0-f50ef2577919", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[57,\n", " 71,\n", " 147,\n", " 151,\n", " 283,\n", " 307,\n", " 313,\n", " 323,\n", " 343,\n", " 351,\n", " 427,\n", " 501,\n", " 633,\n", " 675,\n", " 815,\n", " 851,\n", " 977,\n", " 1079,\n", " 1299,\n", " 1455,\n", " 1493,\n", " 1525,\n", " 1531,\n", " 1763,\n", " 1851,\n", " 1905,\n", " 1993]" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "blanks" ] }, { "cell_type": "code", "execution_count": 21, "id": "27139aed-6b33-41ba-bf5a-4ed33c125118", "metadata": {}, "outputs": [], "source": [ "df.drop(blanks, inplace=True)" ] }, { "cell_type": "code", "execution_count": 22, "id": "bf8a167e-5822-4319-8912-f2b925c432d6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1938, 2)" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.shape" ] }, { "cell_type": "code", "execution_count": 25, "id": "ef17f620-11e4-43fa-9162-a004f4d8f55e", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "X = df['review']\n", "y = df['label']\n", "\n", "X_train, y_train, X_test, y_test = train_test_split(X, y, test_size=0.3, random_state=42)" ] }, { "cell_type": "code", "execution_count": 30, "id": "33580bf3-dca9-4f11-8b8c-ced957a805d3", "metadata": {}, "outputs": [], "source": [ "from sklearn.pipeline import Pipeline\n", "from sklearn.feature_extraction.text import TfidfVectorizer\n", "from sklearn.svm import LinearSVC\n", "\n", "text_clf = Pipeline([\n", " ('tfidf', TfidfVectorizer()),\n", " ('clf', LinearSVC())\n", "])" ] }, { "cell_type": "code", "execution_count": 31, "id": "f9d5765c-bc6a-490e-94d1-72a92cb1fde8", "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "Found input variables with inconsistent numbers of samples: [1356, 582]", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[31], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtext_clf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/base.py:1151\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1144\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[1;32m 1146\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[1;32m 1147\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[1;32m 1148\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[1;32m 1149\u001b[0m )\n\u001b[1;32m 1150\u001b[0m ):\n\u001b[0;32m-> 1151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfit_method\u001b[49m\u001b[43m(\u001b[49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/pipeline.py:420\u001b[0m, in \u001b[0;36mPipeline.fit\u001b[0;34m(self, X, y, **fit_params)\u001b[0m\n\u001b[1;32m 418\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_final_estimator \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpassthrough\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 419\u001b[0m fit_params_last_step \u001b[38;5;241m=\u001b[39m fit_params_steps[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m][\u001b[38;5;241m0\u001b[39m]]\n\u001b[0;32m--> 420\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_final_estimator\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mXt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfit_params_last_step\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 422\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/base.py:1151\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1144\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[1;32m 1146\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[1;32m 1147\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[1;32m 1148\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[1;32m 1149\u001b[0m )\n\u001b[1;32m 1150\u001b[0m ):\n\u001b[0;32m-> 1151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfit_method\u001b[49m\u001b[43m(\u001b[49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/svm/_classes.py:300\u001b[0m, in \u001b[0;36mLinearSVC.fit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m 275\u001b[0m \u001b[38;5;129m@_fit_context\u001b[39m(prefer_skip_nested_validation\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 276\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfit\u001b[39m(\u001b[38;5;28mself\u001b[39m, X, y, sample_weight\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 277\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Fit the model according to the given training data.\u001b[39;00m\n\u001b[1;32m 278\u001b[0m \n\u001b[1;32m 279\u001b[0m \u001b[38;5;124;03m Parameters\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 298\u001b[0m \u001b[38;5;124;03m An instance of the estimator.\u001b[39;00m\n\u001b[1;32m 299\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 300\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_data\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 301\u001b[0m \u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 302\u001b[0m \u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 303\u001b[0m \u001b[43m \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 304\u001b[0m \u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfloat64\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 305\u001b[0m \u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 306\u001b[0m \u001b[43m \u001b[49m\u001b[43maccept_large_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 307\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 308\u001b[0m check_classification_targets(y)\n\u001b[1;32m 309\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclasses_ \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(y)\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/base.py:621\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[0;34m(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)\u001b[0m\n\u001b[1;32m 619\u001b[0m y \u001b[38;5;241m=\u001b[39m check_array(y, input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_y_params)\n\u001b[1;32m 620\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 621\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[43mcheck_X_y\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mcheck_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 622\u001b[0m out \u001b[38;5;241m=\u001b[39m X, y\n\u001b[1;32m 624\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m check_params\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mensure_2d\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mTrue\u001b[39;00m):\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/utils/validation.py:1165\u001b[0m, in \u001b[0;36mcheck_X_y\u001b[0;34m(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)\u001b[0m\n\u001b[1;32m 1147\u001b[0m X \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[1;32m 1148\u001b[0m X,\n\u001b[1;32m 1149\u001b[0m accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1160\u001b[0m input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mX\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 1161\u001b[0m )\n\u001b[1;32m 1163\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_y(y, multi_output\u001b[38;5;241m=\u001b[39mmulti_output, y_numeric\u001b[38;5;241m=\u001b[39my_numeric, estimator\u001b[38;5;241m=\u001b[39mestimator)\n\u001b[0;32m-> 1165\u001b[0m \u001b[43mcheck_consistent_length\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X, y\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/utils/validation.py:409\u001b[0m, in \u001b[0;36mcheck_consistent_length\u001b[0;34m(*arrays)\u001b[0m\n\u001b[1;32m 407\u001b[0m uniques \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(lengths)\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(uniques) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 409\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 410\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound input variables with inconsistent numbers of samples: \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 411\u001b[0m \u001b[38;5;241m%\u001b[39m [\u001b[38;5;28mint\u001b[39m(l) \u001b[38;5;28;01mfor\u001b[39;00m l \u001b[38;5;129;01min\u001b[39;00m lengths]\n\u001b[1;32m 412\u001b[0m )\n", "\u001b[0;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [1356, 582]" ] } ], "source": [ "text_clf.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 32, "id": "f8787363-1a91-4001-9229-ca4543a3762c", "metadata": {}, "outputs": [ { "ename": "NotFittedError", "evalue": "This LinearSVC instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNotFittedError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[32], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtext_clf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_test\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/pipeline.py:508\u001b[0m, in \u001b[0;36mPipeline.predict\u001b[0;34m(self, X, **predict_params)\u001b[0m\n\u001b[1;32m 506\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m _, name, transform \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter(with_final\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m 507\u001b[0m Xt \u001b[38;5;241m=\u001b[39m transform\u001b[38;5;241m.\u001b[39mtransform(Xt)\n\u001b[0;32m--> 508\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msteps\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mXt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mpredict_params\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/linear_model/_base.py:451\u001b[0m, in \u001b[0;36mLinearClassifierMixin.predict\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m 437\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 438\u001b[0m \u001b[38;5;124;03mPredict class labels for samples in X.\u001b[39;00m\n\u001b[1;32m 439\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;124;03m Vector containing the class labels for each sample.\u001b[39;00m\n\u001b[1;32m 449\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 450\u001b[0m xp, _ \u001b[38;5;241m=\u001b[39m get_namespace(X)\n\u001b[0;32m--> 451\u001b[0m scores \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecision_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 452\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(scores\u001b[38;5;241m.\u001b[39mshape) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 453\u001b[0m indices \u001b[38;5;241m=\u001b[39m xp\u001b[38;5;241m.\u001b[39mastype(scores \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m, \u001b[38;5;28mint\u001b[39m)\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/linear_model/_base.py:429\u001b[0m, in \u001b[0;36mLinearClassifierMixin.decision_function\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m 410\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecision_function\u001b[39m(\u001b[38;5;28mself\u001b[39m, X):\n\u001b[1;32m 411\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 412\u001b[0m \u001b[38;5;124;03m Predict confidence scores for samples.\u001b[39;00m\n\u001b[1;32m 413\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 427\u001b[0m \u001b[38;5;124;03m this class would be predicted.\u001b[39;00m\n\u001b[1;32m 428\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 429\u001b[0m \u001b[43mcheck_is_fitted\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 430\u001b[0m xp, _ \u001b[38;5;241m=\u001b[39m get_namespace(X)\n\u001b[1;32m 432\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_data(X, accept_sparse\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcsr\u001b[39m\u001b[38;5;124m\"\u001b[39m, reset\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n", "File \u001b[0;32m/opt/conda/lib/python3.11/site-packages/sklearn/utils/validation.py:1462\u001b[0m, in \u001b[0;36mcheck_is_fitted\u001b[0;34m(estimator, attributes, msg, all_or_any)\u001b[0m\n\u001b[1;32m 1459\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m is not an estimator instance.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m (estimator))\n\u001b[1;32m 1461\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m _is_fitted(estimator, attributes, all_or_any):\n\u001b[0;32m-> 1462\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m NotFittedError(msg \u001b[38;5;241m%\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mtype\u001b[39m(estimator)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m})\n", "\u001b[0;31mNotFittedError\u001b[0m: This LinearSVC instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator." ] } ], "source": [ "text_clf.predict(X_test)" ] }, { "cell_type": "code", "execution_count": null, "id": "0cd3f8c9-aa54-4be8-9ca2-a517968dc4a8", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.4" } }, "nbformat": 4, "nbformat_minor": 5 }