NBSVM Baseline

spanish_joke_classifier_NBSVM_baseline.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "NB-SVM baseline from JHoward\n",
    "https://www.kaggle.com/jhoward/nb-svm-strong-linear-baseline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd, numpy as np\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\n",
    "from pdb import set_trace"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reading the texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_texts_df = pd.read_csv('/home/farzin/rnn_python_code/tweet_es_finetune/haha_2019_train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>text</th>\n",
       "      <th>is_humor</th>\n",
       "      <th>votes_no</th>\n",
       "      <th>votes_1</th>\n",
       "      <th>votes_2</th>\n",
       "      <th>votes_3</th>\n",
       "      <th>votes_4</th>\n",
       "      <th>votes_5</th>\n",
       "      <th>funniness_average</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>705196579758583809</td>\n",
       "      <td>Niveles de retraso mental: \\r\\n\\r\\n— Bajo.\\r\\n...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>678040651817213952</td>\n",
       "      <td>—Vamos Luke desenfunda tu sable, demuestra tu ...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>546750892213829633</td>\n",
       "      <td>- ¿Te ofrezco algo?, ¿Agua, café, mi corazón, ...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>965807211292364801</td>\n",
       "      <td>No se porqué me hago la cabeza deooos</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>638403841839484928</td>\n",
       "      <td>Quisiera saber que hago durante la siesta de l...</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   id                                               text  \\\n",
       "0  705196579758583809  Niveles de retraso mental: \\r\\n\\r\\n— Bajo.\\r\\n...   \n",
       "1  678040651817213952  —Vamos Luke desenfunda tu sable, demuestra tu ...   \n",
       "2  546750892213829633  - ¿Te ofrezco algo?, ¿Agua, café, mi corazón, ...   \n",
       "3  965807211292364801              No se porqué me hago la cabeza deooos   \n",
       "4  638403841839484928  Quisiera saber que hago durante la siesta de l...   \n",
       "\n",
       "   is_humor  votes_no  votes_1  votes_2  votes_3  votes_4  votes_5  \\\n",
       "0         1         1        2        2        0        0        0   \n",
       "1         1         1        3        0        1        0        0   \n",
       "2         1         0        2        1        0        1        1   \n",
       "3         0         3        0        0        0        0        0   \n",
       "4         0         4        0        1        0        0        0   \n",
       "\n",
       "   funniness_average  \n",
       "0                1.5  \n",
       "1                1.5  \n",
       "2                2.6  \n",
       "3                NaN  \n",
       "4                NaN  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_texts_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "rnd_seed = 20190313\n",
    "np.random.seed(rnd_seed)\n",
    "\n",
    "idx = np.random.permutation(len(all_texts_df))\n",
    "test_cut = int(0.15 * len(idx))\n",
    "valid_cut = int(0.15 * len(idx-test_cut))\n",
    "\n",
    "df_train = all_texts_df.iloc[idx[:-(valid_cut+test_cut)],:]\n",
    "df_test  = all_texts_df.iloc[idx[-(valid_cut+test_cut):-test_cut],:]\n",
    "# df_test      = all_texts_df.iloc[idx[-test_cut:],:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((16800, 10), (3600, 10))"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.shape, df_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re, string\n",
    "re_tok = re.compile(f'([{string.punctuation}“”¨«»®´·º½¾¿¡§£₤‘’])')\n",
    "def tokenize(s): \n",
    "    return re_tok.sub(r' \\1 ', s).split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "n = all_texts_df.shape[0]\n",
    "vec = TfidfVectorizer(ngram_range=(1,2), tokenizer=tokenize,\n",
    "               min_df=3, max_df=0.9, strip_accents='unicode', use_idf=1,\n",
    "               smooth_idf=1, sublinear_tf=1 )\n",
    "trn_term_doc = vec.fit_transform(df_train['text'])\n",
    "test_term_doc = vec.transform(df_test['text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<16800x22072 sparse matrix of type '<class 'numpy.float64'>'\n",
       " \twith 388461 stored elements in Compressed Sparse Row format>,\n",
       " <3600x22072 sparse matrix of type '<class 'numpy.float64'>'\n",
       " \twith 79494 stored elements in Compressed Sparse Row format>)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trn_term_doc, test_term_doc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pr(y_i, y):\n",
    "    p = x[y==y_i].sum(0)\n",
    "    return (p+1) / ((y==y_i).sum()+1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = trn_term_doc\n",
    "test_x = test_term_doc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_mdl(y):\n",
    "    y = y.values\n",
    "    r = np.log(pr(1,y) / pr(0,y))\n",
    "    m = LogisticRegression(C=4, dual=True)\n",
    "    x_nb = x.multiply(r)\n",
    "    return m.fit(x_nb, y), r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fit is_humor\n"
     ]
    }
   ],
   "source": [
    "label_cols = ['is_humor']\n",
    "preds = np.zeros((len(df_test), len(label_cols)))\n",
    "\n",
    "for i, j in enumerate(label_cols):\n",
    "    print('fit', j)\n",
    "    m,r = get_mdl(df_train[j])\n",
    "    preds[:,i] = m.predict_proba(test_x.multiply(r))[:,1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "TP = ((preds > 0.5).astype(int) == df_test[label_cols].values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Accuracy: 0.8344444444444444'"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f'Accuracy: {TP.sum() / len(df_test)}'"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.7 fasta.ai1 DEV",
   "language": "python",
   "name": "fastai1_dev"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}