jonas/nlp-lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

simple improvements

Browse Source
This commit is contained in:
Jonas Weinz 2018-07-10 15:59:28 +02:00
parent b4ae0b033e
commit 7f6c9791ae
2 changed files with 17 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
Project/simple_approach/Continous_Learner.ipynb
View File

@ -145,7 +145,7 @@
{ {
"data": { "data": {
"application/vnd.jupyter.widget-view+json": { "application/vnd.jupyter.widget-view+json": {
"model_id": "5a488abefd074719adb15425714a076f", "model_id": "d00ff918ad4d473499b1e91d4dcb8702",
"version_major": 2, "version_major": 2,
"version_minor": 0 "version_minor": 0
}, },
@ -174,7 +174,8 @@
" ],\n", " ],\n",
" [\n", " [\n",
" (widgets.BoundedIntText(value=-1,disabled=True,min=-1, max=10), \"k_means_cluster\"),\n", " (widgets.BoundedIntText(value=-1,disabled=True,min=-1, max=10), \"k_means_cluster\"),\n",
" (widgets.BoundedIntText(value=20,disabled=True,min=-1, max=100), \"n_top_emojis\")\n", " (widgets.BoundedIntText(value=20,disabled=True,min=-1, max=100), \"n_top_emojis\"),\n",
" (widgets.Dropdown(options=[\"latest\", \"mean\"], value=\"latest\"), \"label_criteria\")\n",
" ],\n", " ],\n",
" [\n", " [\n",
" (widgets.Button(disabled=True),\"load_data\")\n", " (widgets.Button(disabled=True),\"load_data\")\n",
@ -446,13 +447,16 @@
" if lemm_and_stemm:\n", " if lemm_and_stemm:\n",
" p_s = progress_indicator(\"stemming progress\")\n", " p_s = progress_indicator(\"stemming progress\")\n",
" \n", " \n",
" emoji_mean = shown_widgets[\"label_criteria\"].value == \"mean\"\n",
" \n",
" sdm = stl.sample_data_manager.generate_and_read(path=shown_widgets[\"root_path\"].value,\n", " sdm = stl.sample_data_manager.generate_and_read(path=shown_widgets[\"root_path\"].value,\n",
" n_top_emojis=shown_widgets[\"n_top_emojis\"].value,\n", " n_top_emojis=shown_widgets[\"n_top_emojis\"].value,\n",
" file_range=range(r[0], r[1]),\n", " file_range=range(r[0], r[1]),\n",
" n_kmeans_cluster=shown_widgets[\"k_means_cluster\"].value,\n", " n_kmeans_cluster=shown_widgets[\"k_means_cluster\"].value,\n",
" read_progress_callback=p_r.update,\n", " read_progress_callback=p_r.update,\n",
" stem_progress_callback=p_s.update if lemm_and_stemm else None,\n", " stem_progress_callback=p_s.update if lemm_and_stemm else None,\n",
" apply_stemming = lemm_and_stemm)\n", " apply_stemming = lemm_and_stemm,\n",
" emoji_mean=emoji_mean)\n",
" shown_widgets[\"batch_size\"].max = len(sdm.labels)\n", " shown_widgets[\"batch_size\"].max = len(sdm.labels)\n",
" \n", " \n",
" \n", " \n",

13
Project/simple_approach/simple_twitter_learning.py
View File

@ -28,6 +28,8 @@ nltk.download('punkt')
nltk.download('averaged_perceptron_tagger') nltk.download('averaged_perceptron_tagger')
nltk.download('wordnet') nltk.download('wordnet')
from keras import losses
# check whether the display function exists: # check whether the display function exists:
try: try:
display display
@ -160,7 +162,7 @@ def batch_lemm(sentences):
class sample_data_manager(object): class sample_data_manager(object):
@staticmethod @staticmethod
def generate_and_read(path:str, only_emoticons=True, apply_stemming=True, n_top_emojis=-1, file_range=None, n_kmeans_cluster=-1, read_progress_callback=None, stem_progress_callback=None): def generate_and_read(path:str, only_emoticons=True, apply_stemming=True, n_top_emojis=-1, file_range=None, n_kmeans_cluster=-1, read_progress_callback=None, stem_progress_callback=None, emoji_mean=False):
""" """
generate, read and process train data in one step. generate, read and process train data in one step.
@ -174,7 +176,7 @@ class sample_data_manager(object):
@return: sample_data_manager object @return: sample_data_manager object
""" """
sdm = sample_data_manager(path) sdm = sample_data_manager(path)
sdm.read_files(file_index_range=range(sdm.n_files) if file_range is None else file_range, only_emoticons=only_emoticons, progress_callback=read_progress_callback) sdm.read_files(file_index_range=range(sdm.n_files) if file_range is None else file_range, only_emoticons=only_emoticons, progress_callback=read_progress_callback, emoji_mean=emoji_mean)
if apply_stemming: if apply_stemming:
sdm.apply_stemming_and_lemmatization(progress_callback=stem_progress_callback) sdm.apply_stemming_and_lemmatization(progress_callback=stem_progress_callback)
@ -641,7 +643,12 @@ class trainer(object):
named_steps[k].fit = lambda X, y: named_steps[k].train_on_batch(to_dense_if_sparse(X), y) # ← why has keras no sparse support on batch progressing!?!?! named_steps[k].fit = lambda X, y: named_steps[k].train_on_batch(to_dense_if_sparse(X), y) # ← why has keras no sparse support on batch progressing!?!?!
if batch_size is None: if batch_size is None:
self.pm.fit(X = self.sdm.X[:max_size], y = self.sdm.y[:max_size]) for e in range(n_epochs):
print("epoch", e)
self.pm.fit(X = self.sdm.X[:max_size], y = self.sdm.y[:max_size])
pred, yt = self.test()
mean_squared_error = ((pred - yt)**2).mean(axis=0)
print("#" + str(e) + ": validation loss: ", mean_squared_error, "scalar: ", np.mean(mean_squared_error))
else: else:
n = len(self.sdm.X) // batch_size n = len(self.sdm.X) // batch_size
for i in range(n_epochs): for i in range(n_epochs):