mirror of
https://github.com/balkian/gists.git
synced 2024-12-24 15:18:13 +00:00
309 lines
7.0 KiB
Plaintext
309 lines
7.0 KiB
Plaintext
|
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 2,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"!bitter tweet get_all lista-tweets.csv"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 3,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"import os"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 6,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"import pandas as pd"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 9,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"df = pd.read_csv('untitled.txt', names=['id', 'label'])"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 10,
|
||
|
"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>label</th>\n",
|
||
|
" </tr>\n",
|
||
|
" </thead>\n",
|
||
|
" <tbody>\n",
|
||
|
" <tr>\n",
|
||
|
" <th>0</th>\n",
|
||
|
" <td>631659865748860929</td>\n",
|
||
|
" <td>ironic</td>\n",
|
||
|
" </tr>\n",
|
||
|
" <tr>\n",
|
||
|
" <th>1</th>\n",
|
||
|
" <td>602202801092038656</td>\n",
|
||
|
" <td>ironic</td>\n",
|
||
|
" </tr>\n",
|
||
|
" </tbody>\n",
|
||
|
"</table>\n",
|
||
|
"</div>"
|
||
|
],
|
||
|
"text/plain": [
|
||
|
" id label\n",
|
||
|
"0 631659865748860929 ironic\n",
|
||
|
"1 602202801092038656 ironic"
|
||
|
]
|
||
|
},
|
||
|
"execution_count": 10,
|
||
|
"metadata": {},
|
||
|
"output_type": "execute_result"
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 14,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"get_text(631659865748860929)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 30,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"import json\n",
|
||
|
"import os\n",
|
||
|
"\n",
|
||
|
"def get_text(tweetid):\n",
|
||
|
" tweetfile = 'tweets/{}.json'.format(tweetid)\n",
|
||
|
" if not os.path.exists(tweetfile):\n",
|
||
|
" return \"\"\n",
|
||
|
" return json.load(open(tweetfile))['text']"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 31,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
"'Uy que emoción! #sarcasmo #noquiero #yatienesuno :( @Cris_baoc https://t.co/Roe4H1D4d6'"
|
||
|
]
|
||
|
},
|
||
|
"execution_count": 31,
|
||
|
"metadata": {},
|
||
|
"output_type": "execute_result"
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"get_text(631659865748860929)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 32,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"df['text'] = df['id'].apply(get_text)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 33,
|
||
|
"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>label</th>\n",
|
||
|
" <th>text</th>\n",
|
||
|
" </tr>\n",
|
||
|
" </thead>\n",
|
||
|
" <tbody>\n",
|
||
|
" <tr>\n",
|
||
|
" <th>0</th>\n",
|
||
|
" <td>631659865748860929</td>\n",
|
||
|
" <td>ironic</td>\n",
|
||
|
" <td>Uy que emoción! #sarcasmo #noquiero #yatienesu...</td>\n",
|
||
|
" </tr>\n",
|
||
|
" <tr>\n",
|
||
|
" <th>1</th>\n",
|
||
|
" <td>602202801092038656</td>\n",
|
||
|
" <td>ironic</td>\n",
|
||
|
" <td></td>\n",
|
||
|
" </tr>\n",
|
||
|
" </tbody>\n",
|
||
|
"</table>\n",
|
||
|
"</div>"
|
||
|
],
|
||
|
"text/plain": [
|
||
|
" id label \\\n",
|
||
|
"0 631659865748860929 ironic \n",
|
||
|
"1 602202801092038656 ironic \n",
|
||
|
"\n",
|
||
|
" text \n",
|
||
|
"0 Uy que emoción! #sarcasmo #noquiero #yatienesu... \n",
|
||
|
"1 "
|
||
|
]
|
||
|
},
|
||
|
"execution_count": 33,
|
||
|
"metadata": {},
|
||
|
"output_type": "execute_result"
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 34,
|
||
|
"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>label</th>\n",
|
||
|
" <th>text</th>\n",
|
||
|
" </tr>\n",
|
||
|
" </thead>\n",
|
||
|
" <tbody>\n",
|
||
|
" <tr>\n",
|
||
|
" <th>0</th>\n",
|
||
|
" <td>631659865748860929</td>\n",
|
||
|
" <td>ironic</td>\n",
|
||
|
" <td>Uy que emoción! #sarcasmo #noquiero #yatienesu...</td>\n",
|
||
|
" </tr>\n",
|
||
|
" </tbody>\n",
|
||
|
"</table>\n",
|
||
|
"</div>"
|
||
|
],
|
||
|
"text/plain": [
|
||
|
" id label \\\n",
|
||
|
"0 631659865748860929 ironic \n",
|
||
|
"\n",
|
||
|
" text \n",
|
||
|
"0 Uy que emoción! #sarcasmo #noquiero #yatienesu... "
|
||
|
]
|
||
|
},
|
||
|
"execution_count": 34,
|
||
|
"metadata": {},
|
||
|
"output_type": "execute_result"
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df[df['text'] != \"\"]"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": []
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"display_name": "Python 3",
|
||
|
"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": "3.6.5"
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 2
|
||
|
}
|