nlp-lab/Project/Tools/emoji tester.ipynb

677 lines
24 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from IPython.display import clear_output, Markdown, Math\n",
"import ipywidgets as widgets\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def create_widgets(t_text, b_text, out, additional_widgets=[]):\n",
" texts = []\n",
" for t in t_text:\n",
" texts.append(widgets.Text(t))\n",
" \n",
" button = widgets.Button(\n",
" description=b_text,\n",
" disabled=False,\n",
" button_style='', # 'success', 'info', 'warning', 'danger' or ''\n",
" tooltip=b_text,\n",
" icon='check'\n",
" )\n",
" display(widgets.VBox([widgets.HBox(texts + additional_widgets + [button]), out]))\n",
" return texts + [button]\n",
"\n",
"out_convert = widgets.Output()\n",
"out_build = widgets.Output()\n",
"out_train = widgets.Output()\n",
"out_save = widgets.Output()\n",
"out_read = widgets.Output()\n",
"out_test = widgets.Output()\n",
"\n",
"def mp(msg):\n",
" display(Markdown(msg))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Emoji Tester\n",
"\n",
"just run all cells at first. Then select on of the actions below."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"## converting plain whatsapp export to csv"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8c94a8d3b3724ad08359817b2086cf85",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Text(value='test.txt'), Button(description='convert whatsapp file to csv', icon='check', style=ButtonStyle(), tooltip='convert whatsapp file to csv'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"## read csv and build database"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ee22e300097e49f1ac24b11662f7dc69",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Text(value='test.txt.csv'), Checkbox(value=False, description='using only last emoji'), Button(description='read', icon='check', style=ButtonStyle(), tooltip='read'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"## Train"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "de06136ee346492d80ef39d304cbc31c",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Dropdown(description='Learning Method', index=1, options=('DecisionTree', 'MLP', 'RandomForest'), value='MLP'), Checkbox(value=False, description='Using one vs all (very slow, only with multi-label!)'), Button(description='train', icon='check', style=ButtonStyle(), tooltip='train'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"## save trained classifier"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b046f3ada7ec4ba7a17965d718552d21",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Text(value='clf.pkl'), Text(value='mlb.pkl'), Text(value='vectorizer.pkl'), Button(description='save classifier', icon='check', style=ButtonStyle(), tooltip='save classifier'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"## import trained classifier"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ac4054e75d8a4214ad040b1b21d6c925",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Text(value='clf.pkl'), Text(value='mlb.pkl'), Text(value='vectorizer.pkl'), Button(description='import classifier', icon='check', style=ButtonStyle(), tooltip='import classifier'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"## predict emoji on custom text"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "db631acbe9c94cac907efaf501a69c6a",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
"<p>\n",
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
" that the widgets JavaScript is still loading. If this message persists, it\n",
" likely means that the widgets JavaScript library is either not installed or\n",
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another frontend (for example, a static\n",
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"VBox(children=(HBox(children=(Text(value=''), Checkbox(value=False, description='Show probabilities (only on trees)'), Button(description='get emoji', icon='check', style=ButtonStyle(), tooltip='get emoji'))), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"mp(\"## converting plain whatsapp export to csv\")\n",
"t_convert, b_convert = create_widgets([\"test.txt\"], \"convert whatsapp file to csv\", out_convert)\n",
"mp(\"## read csv and build database\")\n",
"single_label = widgets.Checkbox(value=False, description='using only last emoji', disable=False)\n",
"t_build, b_build = create_widgets([\"test.txt.csv\"], \"read\", out_build, [single_label])\n",
"mp(\"## Train\")\n",
"d = widgets.Dropdown(options=['DecisionTree', 'MLP', 'RandomForest'], value='MLP', description='Learning Method', disabled=False)\n",
"ova = widgets.Checkbox(value=False, description='Using one vs all (very slow, only with multi-label!)', disabled=False)\n",
"b_train = button = widgets.Button(description=\"train\", disabled=False, button_style='', tooltip=\"train\",icon='check')\n",
"display(widgets.VBox([widgets.HBox([d,ova,b_train]), out_train]))\n",
"mp(\"## save trained classifier\")\n",
"t_save_c, t_save_m, t_save_v, b_save = create_widgets([\"clf.pkl\", \"mlb.pkl\", \"vectorizer.pkl\"], \"save classifier\", out_save)\n",
"mp(\"## import trained classifier\")\n",
"t_read_c, t_read_m, t_read_v, b_read = create_widgets([\"clf.pkl\", \"mlb.pkl\", \"vectorizer.pkl\"], \"import classifier\", out_read)\n",
"mp(\"## predict emoji on custom text\")\n",
"b_prop = widgets.Checkbox(value=False, description='Show probabilities (only on trees)', disabled=False)\n",
"t_test, b_test = create_widgets([\"\"], \"get emoji\", out_test,[b_prop])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"----\n",
"## Code Section:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def convert(b):\n",
" with out_convert:\n",
" clear_output()\n",
" with out_convert:\n",
" mp(\"**converting \" + t_convert.value + \"…**\")\n",
" import subprocess\n",
" print(str(subprocess.check_output([\"./whatsapp2csv.sh\", t_convert.value])).strip())\n",
" mp(\"**done**\")\n",
"\n",
"b_convert.on_click(convert)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* download emoji specification if not already existing"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"found existing emoji specification\n"
]
}
],
"source": [
"%%bash\n",
"if [ ! -e emoji-data.txt ]\n",
"then\n",
" echo \"downloading emoji specification\"\n",
" wget https://www.unicode.org/Public/emoji/11.0/emoji-data.txt\n",
"else\n",
" echo \"found existing emoji specification\"\n",
"fi\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* stuff for creating emoji database"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"emoji_blacklist = set([\n",
" 0x1F3FB,\n",
" 0x1F3FC,\n",
" 0x1F3FD,\n",
" 0x1F3FE,\n",
" 0x1F3FF,\n",
" 0x2642,\n",
" 0x2640\n",
"])\n",
"\n",
"emoji_code_set = None\n",
"\n",
"def create_emoji_set():\n",
" global emoji_code_set\n",
" \n",
" emoji_data = pd.read_csv('emoji-data.txt', delimiter=';', comment='#', names=[\"unicode\",\"type\"])\n",
" emoji_data['type'] = emoji_data['type'].str.strip()\n",
" emoji_data = emoji_data[emoji_data['type'] == \"Emoji_Presentation\"]\n",
" \n",
" emoji_codes = emoji_data['unicode']\n",
" emoji_codes.head()\n",
" \n",
" emoji_code_list = []\n",
" for entry in emoji_codes:\n",
" # testing whether we have an entry or a range:\n",
" if '.' in entry:\n",
" # range\n",
" a,b = entry.split(\"..\")\n",
" for i in range(int(a,16),int(b,16) +1):\n",
" if i not in emoji_blacklist:\n",
" emoji_code_list.append(i)\n",
" else:\n",
" # single entry\n",
" if i not in emoji_blacklist:\n",
" emoji_code_list.append(int(entry,16))\n",
" emoji_code_set = set(emoji_code_list)\n",
" display(Markdown(\"**imported Emojis** (without modifier):\\n>\" + \"\".join([chr(x) for x in emoji_code_set])))\n",
" display(Markdown(\"**blacklisted Emojis:**\\n>\" + \"\".join([chr(x) for x in emoji_blacklist])))\n",
" f = open('emoji-list.txt', 'w')\n",
" for e in emoji_code_set:\n",
" f.write(chr(e) + \"\\n\")\n",
" f.close()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* stuff for reading whatsapp messages"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"messages = None\n",
"vectorizer = None\n",
"clf_a = None\n",
"mlb = None\n",
"\n",
"emoji_messages=None"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def read_message_and_build_db(filename):\n",
" global messages\n",
" global emoji_messages\n",
" global vectorizer\n",
" global clf_a\n",
" global mlb\n",
" \n",
" messages = pd.read_csv(filename, delimiter='\\t')\n",
" mp(\"**filter messages and creating labels. This can take a while...**\")\n",
" messages[\"emojis\"] = None\n",
" \n",
" msg_batchsize = 1000\n",
" msg_counter = 0\n",
" \n",
" for i in messages.index:\n",
" \n",
" msg_counter+=1\n",
" if msg_counter >= msg_batchsize:\n",
" print(str(100 * i / messages.shape[0]) + \"%\")\n",
" msg_counter=0\n",
" \n",
" emoji_list = []\n",
" m = messages.iloc[i]['message']\n",
" m_new = \"\"\n",
" for c in str(m):\n",
" if ord(c) in emoji_code_set:\n",
" emoji_list.append(c)\n",
" elif ord(c) not in emoji_blacklist:\n",
" m_new += c\n",
" # if single label: only use last found emoji\n",
" messages.loc[i,'emojis'] = set(emoji_list) if (not single_label.value) or len(emoji_list)==0 else set(emoji_list[-1])\n",
" #remove emiójis from message\n",
" messages.loc[i,'message'] = m_new\n",
" \n",
" emoji_messages = messages[[True if len(e) > 0 else False for e in messages['emojis']]]\n",
" emoji_messages = emoji_messages[emoji_messages['message'] != \"\"]\n",
" \n",
" mp(\"**Done**\")\n",
" \n",
" display(emoji_messages)\n",
"\n",
"def train(b):\n",
" global messages\n",
" global emoji_messages\n",
" global vectorizer\n",
" global clf_a\n",
" global mlb\n",
" with out_train:\n",
" clear_output()\n",
" # train part:\n",
" import numpy as np\n",
" import itertools\n",
" import sklearn.utils as sku\n",
" from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, HashingVectorizer\n",
" from sklearn.model_selection import train_test_split\n",
" from sklearn.preprocessing import MultiLabelBinarizer\n",
"\n",
" mlb = MultiLabelBinarizer() if not single_label.value else None\n",
" \n",
" if not mlb:\n",
" l = [list(e)[-1] for e in emoji_messages['emojis']]\n",
" \n",
" labels=mlb.fit_transform(emoji_messages['emojis']) if mlb else l\n",
" \n",
" if mlb:\n",
" display(Markdown(\"**emojis contained in Dataset:**\\n >\" + \"\".join(mlb.classes_ )))\n",
" else:\n",
" display(Markdown(\"**emojis contained in Dataset:**\\n >\" + \"\".join(set(l))))\n",
"\n",
" X1, Xt1, y1, yt1 = train_test_split(emoji_messages['message'], labels, test_size=0.1, random_state=4222)\n",
"\n",
" vectorizer = TfidfVectorizer(stop_words='english')\n",
" vec_train = vectorizer.fit_transform(X1)\n",
" vec_test = vectorizer.transform(Xt1)\n",
"\n",
" mp(\"**train classifier. This can take a very long time… Grab a coffe! 😀**\")\n",
"\n",
" from sklearn.ensemble import RandomForestClassifier as RFC\n",
" from sklearn.neural_network import MLPClassifier as MLP\n",
" #from sklearn.naive_bayes import MultinomialNB as MNB\n",
" from sklearn.tree import DecisionTreeClassifier as DTC\n",
" from sklearn.multiclass import OneVsRestClassifier as OVRC\n",
" clf_a = None\n",
" if (d.value == \"DecisionTree\"):\n",
" clf_a = DTC()\n",
" elif d.value == \"MLP\":\n",
" clf_a = MLP(hidden_layer_sizes=(64,))\n",
" elif d.value == \"RandomForest\":\n",
" RFC(criterion='entropy', random_state=4222)\n",
"\n",
" if ova.value:\n",
" clf_a=OVRC(clf_a)\n",
"\n",
" display(clf_a)\n",
" clf_a.fit(vec_train, y1)\n",
"\n",
" mp(\"**training done**\")\n",
"\n",
" pred = clf_a.predict(vectorizer.transform(Xt1))\n",
"\n",
" testlist = pd.DataFrame({'message': Xt1, 'pred': mlb.inverse_transform(pred) if mlb else pred, 'teacher': mlb.inverse_transform(yt1) if mlb else yt1})\n",
" testlist.to_csv('export.csv')\n",
" display(testlist)\n",
" \n",
"def build_db(b):\n",
" with out_build:\n",
" clear_output()\n",
" create_emoji_set()\n",
" read_message_and_build_db(t_build.value)\n",
"b_build.on_click(build_db)\n",
"b_train.on_click(train)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.externals import joblib\n",
"def write_to_file(b):\n",
" global vectorizer\n",
" global clf_a\n",
" global mlb\n",
" \n",
" with out_save:\n",
" clear_output()\n",
" mp(\"**write to file...**\")\n",
" joblib.dump(clf_a, t_save_c.value)\n",
" if mlb:\n",
" joblib.dump(mlb, t_save_m.value) \n",
" joblib.dump(vectorizer, t_save_v.value)\n",
" mp(\"**done**\")\n",
"b_save.on_click(write_to_file)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def read_from_file(b):\n",
" global vectorizer\n",
" global clf_a\n",
" global mlb\n",
" \n",
" with out_read:\n",
" clear_output()\n",
" mp(\"**read from file…**\")\n",
" clf_a = joblib.load(t_read_c.value)\n",
" if t_read_m.value != \"\":\n",
" mlb = joblib.load(t_read_m.value)\n",
" else:\n",
" mlb = None\n",
" vectorizer = joblib.load(t_read_v.value)\n",
" mp(\"**done**\")\n",
"b_read.on_click(read_from_file)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"def predict(b):\n",
" with out_test:\n",
" clear_output()\n",
" v = mlb.inverse_transform(clf_a.predict(vectorizer.transform([t_test.value])))[0] if mlb else clf_a.predict(vectorizer.transform([t_test.value]))[0]\n",
" mp(\"**prediction:**\\n# \" + (\"\".join(v) if len(v)>0 else \" \"))\n",
" if b_prop.value:\n",
" pred = clf_a.predict_proba(vectorizer.transform([t_test.value]))\n",
" print(mlb.inverse_transform(pred))\n",
"\n",
"b_test.on_click(predict)"
]
},
{
"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
}