updated notebook according to changes in the python file

This commit is contained in:
Jonas Weinz 2018-06-26 14:47:39 +02:00
parent df811196e5
commit 10fd5817e7

View File

@ -2,43 +2,9 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/jonas/.local/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
" from ._conv import register_converters as _register_converters\n",
"Using TensorFlow backend.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to /home/jonas/nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package averaged_perceptron_tagger to\n",
"[nltk_data] /home/jonas/nltk_data...\n",
"[nltk_data] Package averaged_perceptron_tagger is already up-to-\n",
"[nltk_data] date!\n",
"[nltk_data] Downloading package wordnet to /home/jonas/nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"import pandas as pd\n",
"from IPython.display import clear_output, Markdown, Math\n",
@ -59,6 +25,7 @@
"import pickle\n",
"import operator\n",
"from sklearn.pipeline import Pipeline\n",
"import json\n",
"nltk.download('punkt')\n",
"nltk.download('averaged_perceptron_tagger')\n",
"nltk.download('wordnet')"
@ -66,7 +33,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -84,7 +51,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -109,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -129,7 +96,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -154,7 +121,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -194,13 +161,13 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"class sample_data_manager(object):\n",
" @staticmethod\n",
" def generate_and_read(path:str, only_emoticons=True, apply_stemming=True, n_top_emojis=-1, file_range=None, n_kmeans_cluster=-1):\n",
" def generate_and_read(path:str, only_emoticons=True, apply_stemming=True, n_top_emojis=-1, file_range=None, n_kmeans_cluster=-1, progress_callback=None):\n",
" \"\"\"\n",
" generate, read and process train data in one step.\n",
" \n",
@ -214,7 +181,7 @@
" @return: sample_data_manager object\n",
" \"\"\"\n",
" sdm = sample_data_manager(path)\n",
" sdm.read_files(file_index_range=range(sdm.n_files) if file_range is None else file_range, only_emoticons=only_emoticons)\n",
" sdm.read_files(file_index_range=range(sdm.n_files) if file_range is None else file_range, only_emoticons=only_emoticons, progress_callback=progress_callback)\n",
" if apply_stemming:\n",
" sdm.apply_stemming_and_lemmatization()\n",
" \n",
@ -254,7 +221,7 @@
" self.kmeans_cluster = None\n",
" self.label_binarizer = None\n",
" \n",
" def read_files(self, file_index_range:list, only_emoticons=True):\n",
" def read_files(self, file_index_range:list, only_emoticons=True, progress_callback=None):\n",
" \"\"\"\n",
" reading (multiple) files to one panda table.\n",
" \n",
@ -268,7 +235,8 @@
" self.raw_data = pd.read_json(self.json_files[i], encoding=\"utf-8\")\n",
" else:\n",
" self.raw_data = self.raw_data.append(pd.read_json(self.json_files[i], encoding=\"utf-8\"))\n",
" \n",
" if progress_callback is not None:\n",
" progress_callback()\n",
" self.emojis = self.raw_data['EMOJI']\n",
" self.plain_text = self.raw_data['text']\n",
" \n",
@ -396,8 +364,7 @@
" \n",
" labels = self.binary_labels if self.use_binary_labels else self.labels\n",
" assert labels is not None\n",
" self.X, self.Xt, self.y, self.yt = train_test_split(self.plain_text, labels, test_size=split, random_state=random_state)\n",
"\n"
" self.X, self.Xt, self.y, self.yt = train_test_split(self.plain_text, labels, test_size=split, random_state=random_state)\n"
]
},
{
@ -409,12 +376,26 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"class pipeline_manager(object):\n",
" @staticmethod\n",
" def load_from_pipeline_file(pipeline_file:str):\n",
" \"\"\"\n",
" loading a json configuration file and using it's paramters to call 'load_pipeline_from_files'\n",
" \"\"\"\n",
" with open(pipeline_file, 'r') as f:\n",
" d = json.load(f)\n",
" \n",
" keras_models = d['keras_models']\n",
" all_models = d['all_models']\n",
" \n",
" return pipeline_manager.load_pipeline_from_files(pipeline_file.rsplit('.',1)[0], keras_models, all_models)\n",
"\n",
"\n",
" @staticmethod\n",
" def load_pipeline_from_files(file_prefix:str, keras_models = [], all_models = []):\n",
" \"\"\"\n",
" load a pipeline from files. A pipeline should be represented by multiple model files in the form '<file_prefix>.<model_name>'\n",
@ -527,6 +508,7 @@
" @param prefix: file prefix for all models\n",
" \"\"\"\n",
" \n",
"\n",
" print(self.keras_models)\n",
" # doing this like explained here: https://stackoverflow.com/a/43415459\n",
" for step in self.pipeline.named_steps:\n",
@ -539,6 +521,9 @@
" load_command += prefix + \"', \" + str(self.keras_models) + \", \"\n",
" load_command += str(list(self.pipeline.named_steps.keys())) + \")\"\n",
"\n",
" with open(prefix + '.pipeline', 'w') as outfile:\n",
" json.dump({'keras_models': self.keras_models, 'all_models': [step for step in self.pipeline.named_steps]}, outfile)\n",
" \n",
" import __main__ as main\n",
" if not hasattr(main, '__file__'):\n",
" display(\"saved pipeline. It can be loaded the following way:\")\n",
@ -584,7 +569,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -594,7 +579,7 @@
" self.sdm = sdm\n",
" self.pm = pm\n",
" \n",
" def fit(self, max_size=10000, disabled_fit_steps=['vectorizer']):\n",
" def fit(self, max_size=10000, disabled_fit_steps=['vectorizer'], keras_batch_fitting_layer=['keras_model'], batch_size=None, n_epochs=1, progress_callback=None):\n",
" \"\"\"\n",
" fitting data in the pipeline. Because we don't want to refit the vectorizer, the pipeline models containing the vectorizer have to be named explicitly\n",
" \n",
@ -607,32 +592,52 @@
" disabled_fits = {}\n",
" disabled_fit_transforms = {}\n",
" \n",
" disabled_keras_fits = {}\n",
" \n",
" named_steps = self.pm.pipeline.named_steps\n",
" \n",
" for s in disabled_fit_steps:\n",
" # now it gets a little bit dirty:\n",
" # now it gets really dirty:\n",
" # replace fit functions we don't want to call again (e.g. for vectorizers)\n",
" disabled_fits[s] = named_steps[s].fit\n",
" disabled_fit_transforms[s] = named_steps[s].fit_transform\n",
" named_steps[s].fit = lambda self, X, y=None: self\n",
" named_steps[s].fit_transform = named_steps[s].transform\n",
" \n",
" for k in keras_batch_fitting_layer:\n",
" # forcing batch fitting on keras\n",
" disabled_keras_fits[k]=named_steps[k].fit\n",
" named_steps[k].fit = lambda X, y: named_steps[k].train_on_batch(X.todense(), y) # ← why has keras no sparse support on batch progressing!?!?!\n",
" \n",
" if batch_size is None:\n",
" self.pm.fit(X = self.sdm.X[:max_size], y = self.sdm.y[:max_size])\n",
" else:\n",
" n = len(self.sdm.X) // batch_size\n",
" for i in range(n_epochs):\n",
" for j in range(n):\n",
" self.pm.fit(X = np.array(self.sdm.X[j*batch_size:(j+1)*batch_size]), y = np.array(self.sdm.y[j*batch_size:(j+1)*batch_size]))\n",
" if progress_callback is not None:\n",
" progress_callback()\n",
" pred, yt = self.test()\n",
" mean_squared_error = ((pred - yt)**2).mean(axis=0)\n",
" print(\"#\" + str(j) + \": loss: \", mean_squared_error)\n",
"\n",
" \n",
" # restore replaced fit functions:\n",
" for s in disabled_fit_steps:\n",
" named_steps[s].fit = disabled_fits[s]\n",
" named_steps[s].fit_transform = disabled_fit_transforms[s]\n",
" \n",
" for k in keras_batch_fitting_layer:\n",
" named_steps[k].fit = disabled_keras_fits[k]\n",
" \n",
" def test(self):\n",
" '''\n",
" @return: prediction:list, teacher:list\n",
" '''\n",
" if self.sdm.X is None:\n",
" self.sdm.create_train_test_split()\n",
" return self.pm.predict(self.sdm.Xt), self.sdm.yt\n",
"\n",
" "
" return self.pm.predict(self.sdm.Xt), self.sdm.yt\n"
]
},
{
@ -652,21 +657,9 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"reading file: ./data_en/2017-11-01.json...\n",
"imported 33368 samples\n",
"remaining samples after top emoji filtering: 26197\n",
"Epoch 1/1\n",
"100/100 [==============================] - 3s 28ms/step - loss: 0.1230\n"
]
}
],
"outputs": [],
"source": [
"import __main__ as main\n",
"if not hasattr(main, '__file__'):\n",
@ -698,40 +691,9 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['keras_model']\n"
]
},
{
"data": {
"text/plain": [
"'saved pipeline. It can be loaded the following way:'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"> ```\n",
"pipeline_manager.load_pipeline_from_files( 'custom_classifier', ['keras_model'], ['vectorizer', 'keras_model'])\n",
"```"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import __main__ as main\n",
"if not hasattr(main, '__file__'):\n",
@ -750,156 +712,9 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0.16062996, 0.08324276, 0.09433182],\n",
" [0.16413 , 0.09421383, 0.07578427],\n",
" [0.11994962, 0.05705731, 0.06310127],\n",
" ...,\n",
" [0.13887292, 0.08502828, 0.08176519],\n",
" [0.18185864, 0.09223703, 0.10704609],\n",
" [0.17687687, 0.09147045, 0.10650696]], dtype=float32)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"array([[0.46813021, 0.24716181, 0.28470797],\n",
" [0.46813021, 0.24716181, 0.28470797],\n",
" [0.70401758, 0.05932203, 0.23666039],\n",
" ...,\n",
" [0.46813021, 0.24716181, 0.28470797],\n",
" [0.46813021, 0.24716181, 0.28470797],\n",
" [0.46813021, 0.24716181, 0.28470797]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"prediction variance: 0.0005431187\n",
"teacher variance: 0.03341702104519965\n"
]
},
{
"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>predict</th>\n",
" <th>predicted_sentiment</th>\n",
" <th>teacher</th>\n",
" <th>teacher_sentiment</th>\n",
" <th>text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>35671</th>\n",
" <td>😂</td>\n",
" <td>[0.16062995791435242, 0.0832427591085434, 0.09...</td>\n",
" <td>😂</td>\n",
" <td>[0.46813021474490496, 0.24716181096977158, 0.2...</td>\n",
" <td>i feel like i care so much more in everi situat</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25683</th>\n",
" <td>😢</td>\n",
" <td>[0.16413000226020813, 0.0942138284444809, 0.07...</td>\n",
" <td>😂</td>\n",
" <td>[0.46813021474490496, 0.24716181096977158, 0.2...</td>\n",
" <td>i did not meat to add that 2 there ... hav see...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8985</th>\n",
" <td>😂</td>\n",
" <td>[0.11994962394237518, 0.05705730617046356, 0.0...</td>\n",
" <td>😊</td>\n",
" <td>[0.7040175768989329, 0.059322033898305086, 0.2...</td>\n",
" <td>never…</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5410</th>\n",
" <td>😂</td>\n",
" <td>[0.18114930391311646, 0.10199417173862457, 0.1...</td>\n",
" <td>😂</td>\n",
" <td>[0.46813021474490496, 0.24716181096977158, 0.2...</td>\n",
" <td>lmao on me ! ! ! wtf wa he suppos to say</td>\n",
" </tr>\n",
" <tr>\n",
" <th>62611</th>\n",
" <td>😂</td>\n",
" <td>[0.16997836530208588, 0.08633847534656525, 0.0...</td>\n",
" <td>😊</td>\n",
" <td>[0.7040175768989329, 0.059322033898305086, 0.2...</td>\n",
" <td>this dude alway help me get through my school ...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" predict predicted_sentiment teacher \\\n",
"35671 😂 [0.16062995791435242, 0.0832427591085434, 0.09... 😂 \n",
"25683 😢 [0.16413000226020813, 0.0942138284444809, 0.07... 😂 \n",
"8985 😂 [0.11994962394237518, 0.05705730617046356, 0.0... 😊 \n",
"5410 😂 [0.18114930391311646, 0.10199417173862457, 0.1... 😂 \n",
"62611 😂 [0.16997836530208588, 0.08633847534656525, 0.0... 😊 \n",
"\n",
" teacher_sentiment \\\n",
"35671 [0.46813021474490496, 0.24716181096977158, 0.2... \n",
"25683 [0.46813021474490496, 0.24716181096977158, 0.2... \n",
"8985 [0.7040175768989329, 0.059322033898305086, 0.2... \n",
"5410 [0.46813021474490496, 0.24716181096977158, 0.2... \n",
"62611 [0.7040175768989329, 0.059322033898305086, 0.2... \n",
"\n",
" text \n",
"35671 i feel like i care so much more in everi situat \n",
"25683 i did not meat to add that 2 there ... hav see... \n",
"8985 never… \n",
"5410 lmao on me ! ! ! wtf wa he suppos to say \n",
"62611 this dude alway help me get through my school ... "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Squared Error: [0.13877691 0.04682433 0.02937794]\n",
"Variance teacher: [0.02183094 0.02513847 0.00285735]\n",
"Variance prediction: [0.00046378 0.00019441 0.00020516]\n"
]
}
],
"outputs": [],
"source": [
"import __main__ as main\n",
"if not hasattr(main, '__file__'):\n",
@ -945,68 +760,9 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "003ae16760b04c25bdc9f2fe2193747a",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type <code>Text</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": [
"Text(value='')"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4580af82b30545f197a41e4359010556",
"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=(Button(description='get emoji', icon='check', style=ButtonStyle(), tooltip='Click me'), Output()))"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import __main__ as main\n",
"if not hasattr(main, '__file__'):\n",