530 lines
14 KiB
Plaintext
530 lines
14 KiB
Plaintext
{
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0,
|
|
"metadata": {
|
|
"colab": {
|
|
"name": "Paranormal or skeptic.ipynb",
|
|
"provenance": [],
|
|
"collapsed_sections": [],
|
|
"toc_visible": true
|
|
},
|
|
"kernelspec": {
|
|
"name": "python3",
|
|
"display_name": "Python 3"
|
|
}
|
|
},
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "x8uZz8__5sXr",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"\n",
|
|
"# Loading Data\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "NQFKg_czGeRA",
|
|
"colab_type": "code",
|
|
"outputId": "60d1c52a-8b42-4a26-d878-67f284589917",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 34
|
|
}
|
|
},
|
|
"source": [
|
|
"!xzcat train/in.tsv.xz | wc -l"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"text": [
|
|
"289579\n"
|
|
],
|
|
"name": "stdout"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "GxUYlO5M6SOJ",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import seaborn as sns\n",
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"from scipy.sparse import hstack\n",
|
|
"import csv\n",
|
|
"import datetime"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "MWDzekYY6S9f",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer\n",
|
|
"from sklearn.pipeline import Pipeline\n",
|
|
"from sklearn.linear_model import SGDClassifier\n",
|
|
"from sklearn.naive_bayes import MultinomialNB,ComplementNB,BernoulliNB,GaussianNB"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "SrLtGV3p4pKW",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"def load_set(path, isTest):\n",
|
|
" dataset = pd.read_csv(path+\"/in.tsv.xz\", delimiter=\"\\t\",header=None,names=[\"text\",\"date\"],quoting=csv.QUOTE_NONE)\n",
|
|
" dataset[\"date\"] = pd.to_datetime(dataset[\"date\"].apply(lambda x: datetime.datetime.fromtimestamp(x).isoformat()))\n",
|
|
" if not isTest:\n",
|
|
" expected = pd.read_csv(path+\"/expected.tsv\",header=None,names=[\"class\"],dtype=\"category\")\n",
|
|
" return dataset, expected\n",
|
|
" return dataset"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "wH70ClgjBeCO",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"**Load all sets**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "huOmuCrE6yCR",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"train_set, expected_train = load_set(\"train\", False)\n",
|
|
"dev_set, expected_dev = load_set(\"dev-0\", False)\n",
|
|
"test_set = load_set(\"test-A\", True)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "mWO1IroV6cmm",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"# Prepare data"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "VVd7DJ1E6cOO",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"def prepare_data(data):\n",
|
|
" data[\"day\"] = data[\"date\"].dt.day\n",
|
|
" data[\"month\"] = data[\"date\"].dt.month\n",
|
|
" data[\"year\"] = data[\"date\"].dt.year\n",
|
|
" return data"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "i_k63XB5642m",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"train_set = prepare_data(train_set)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "dcjUSa7f7Wex",
|
|
"colab_type": "code",
|
|
"outputId": "9fa0ca70-0516-4656-a1d5-641e5b0f41ff",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 204
|
|
}
|
|
},
|
|
"source": [
|
|
"train_set.sample(5)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": [
|
|
{
|
|
"output_type": "execute_result",
|
|
"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>text</th>\n",
|
|
" <th>date</th>\n",
|
|
" <th>day</th>\n",
|
|
" <th>month</th>\n",
|
|
" <th>year</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>103770</th>\n",
|
|
" <td>Holy crap. I don't think I've seen or heard o...</td>\n",
|
|
" <td>2010-07-16 19:27:08</td>\n",
|
|
" <td>16</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>2010</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>240391</th>\n",
|
|
" <td>You lost all pretense of civility with your ar...</td>\n",
|
|
" <td>2010-09-30 12:18:36</td>\n",
|
|
" <td>30</td>\n",
|
|
" <td>9</td>\n",
|
|
" <td>2010</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>220910</th>\n",
|
|
" <td>What do people think of ghost adventures? Cur...</td>\n",
|
|
" <td>2012-08-21 19:59:56</td>\n",
|
|
" <td>21</td>\n",
|
|
" <td>8</td>\n",
|
|
" <td>2012</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>39644</th>\n",
|
|
" <td>Congrats on getting the joke.</td>\n",
|
|
" <td>2011-07-29 18:19:46</td>\n",
|
|
" <td>29</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>2011</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>220867</th>\n",
|
|
" <td>We live in a world where any media can be copi...</td>\n",
|
|
" <td>2012-07-18 08:53:24</td>\n",
|
|
" <td>18</td>\n",
|
|
" <td>7</td>\n",
|
|
" <td>2012</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" text ... year\n",
|
|
"103770 Holy crap. I don't think I've seen or heard o... ... 2010\n",
|
|
"240391 You lost all pretense of civility with your ar... ... 2010\n",
|
|
"220910 What do people think of ghost adventures? Cur... ... 2012\n",
|
|
"39644 Congrats on getting the joke. ... 2011\n",
|
|
"220867 We live in a world where any media can be copi... ... 2012\n",
|
|
"\n",
|
|
"[5 rows x 5 columns]"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"execution_count": 12
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "hIZZ9vcu5Xx7",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"# Train"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "yqHuHTyI8Kfz",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"vectorize = CountVectorizer(stop_words='english',ngram_range=(1,3),strip_accents='ascii')\n",
|
|
"vectorized = vectorize.fit_transform(train_set[\"text\"])"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "ZaLsOdPe9aFu",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"X = vectorized\n",
|
|
"y = expected_train[\"class\"]"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "CeYlhwda9Sa7",
|
|
"colab_type": "code",
|
|
"outputId": "607d4f8f-f632-4d41-a1ab-e5d020cc00ae",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 34
|
|
}
|
|
},
|
|
"source": [
|
|
"bayes = MultinomialNB(alpha=0.4)\n",
|
|
"bayes.fit(X,y)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": [
|
|
{
|
|
"output_type": "execute_result",
|
|
"data": {
|
|
"text/plain": [
|
|
"MultinomialNB(alpha=0.4, class_prior=None, fit_prior=True)"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"execution_count": 15
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "SaIcL28I-JCK",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"# Predict and evaluate"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "q34dlX_43ZoV",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"def predict_data(data):\n",
|
|
" prepared = prepare_data(data)\n",
|
|
" vectorized = vectorize.transform(data[\"text\"])\n",
|
|
" predicted = bayes.predict(vectorized)\n",
|
|
" return predicted"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "9sLnLLEUHgoM",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"dev_predicted = predict_data(dev_set)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "yigVrrVJHkob",
|
|
"colab_type": "code",
|
|
"outputId": "9491f926-94a3-4310-9f63-be937663489d",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 34
|
|
}
|
|
},
|
|
"source": [
|
|
"np.mean(dev_predicted == expected_dev[\"class\"])"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": [
|
|
{
|
|
"output_type": "execute_result",
|
|
"data": {
|
|
"text/plain": [
|
|
"0.8201820940819423"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"execution_count": 19
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "gPdE2HK64aRZ",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"test_predicted = predict_data(test_set)"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "QFxuvfUJ8AhJ",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"**Clean output for saving**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "zjypBm1260h1",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"test_predicted = np.array([item.strip() for item in test_predicted])\n",
|
|
"dev_predicted = np.array([item.strip() for item in dev_predicted])"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "baJydHEl4H7N",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"**Save to file**\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "O6gyoEJf4KhS",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"np.savetxt('test-A/out.tsv', test_predicted, '%c')\n",
|
|
"np.savetxt('dev-0/out.tsv', dev_predicted, '%c')"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "jIG2Fxrm89D7",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"**Check geval output**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "mnch9uLE8vkK",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"!wget https://gonito.net/get/bin/geval\n",
|
|
"!chmod u+x geval"
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "oEkjIcwe8zef",
|
|
"colab_type": "code",
|
|
"outputId": "cdb6473e-4eb9-48a7-cc25-25a193cc9194",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 34
|
|
}
|
|
},
|
|
"source": [
|
|
"!./geval -t \"dev-0\""
|
|
],
|
|
"execution_count": 0,
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"text": [
|
|
"0.8202\n"
|
|
],
|
|
"name": "stdout"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
} |