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

plotting validation error

Browse Source
This commit is contained in:
Jonas Weinz 2018-07-21 09:48:25 +02:00
parent 16e3cb84a0
commit 1c8c15b0d5
2 changed files with 34 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
Project/simple_approach/Continous_Learner.ipynb
View File

@ -11,7 +11,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -60,7 +69,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -115,7 +124,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -145,7 +154,7 @@
{ {
"data": { "data": {
"application/vnd.jupyter.widget-view+json": { "application/vnd.jupyter.widget-view+json": {
"model_id": "ef207b9276fc4a84b46053e7d979f2a2", "model_id": "3e7d23dfb4b24f888d95bbd416565026",
"version_major": 2, "version_major": 2,
"version_minor": 0 "version_minor": 0
}, },
@ -271,7 +280,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -289,7 +298,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -377,7 +386,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -401,7 +410,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -478,7 +487,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -522,7 +531,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -598,7 +607,7 @@
" mp(\"**layers:** \")\n", " mp(\"**layers:** \")\n",
" jp(layers, headers=['#neurons', 'activation_func'])\n", " jp(layers, headers=['#neurons', 'activation_func'])\n",
"\n", "\n",
" pm = stl.pipeline_manager.create_keras_pipeline_with_vectorizer(vectorizer, layers=layers, sdm=sdm)\n", " pm = stl.pipeline_manager.create_keras_pipeline_with_vectorizer(vectorizer, layers=layers, sdm=sdm, fit_vectorizer=not shown_widgets[\"d2v_use_pretrained\"].value)\n",
"\n", "\n",
"def save_classifier(b):\n", "def save_classifier(b):\n",
" global sdm\n", " global sdm\n",
@ -659,7 +668,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -685,7 +694,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -694,7 +703,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -704,7 +713,7 @@
"traceback": [ "traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-12-beaf1df9153b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mv\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpipeline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnamed_steps\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'vectorizer'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"I am sad\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;32m<ipython-input-13-beaf1df9153b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mv\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpipeline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnamed_steps\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'vectorizer'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"I am sad\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'pipeline'" "\u001b[0;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'pipeline'"
] ]
} }

10
Project/simple_approach/simple_twitter_learning.py
View File

@ -25,6 +25,7 @@ import operator
from sklearn.pipeline import Pipeline from sklearn.pipeline import Pipeline
import json import json
import datetime import datetime
import matplotlib.pyplot as plt
nltk.download('punkt') nltk.download('punkt')
nltk.download('averaged_perceptron_tagger') nltk.download('averaged_perceptron_tagger')
@ -657,6 +658,8 @@ class trainer(object):
"""constructor""" """constructor"""
self.sdm = sdm self.sdm = sdm
self.pm = pm self.pm = pm
self.acc = []
self.val = []
def fit(self, max_size=1000000, disabled_fit_steps=['vectorizer'], keras_batch_fitting_layer=['keras_model'], batch_size=None, n_epochs=1, progress_callback=None): def fit(self, max_size=1000000, disabled_fit_steps=['vectorizer'], keras_batch_fitting_layer=['keras_model'], batch_size=None, n_epochs=1, progress_callback=None):
""" """
@ -691,12 +694,19 @@ 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.acc = []
self.val = []
for e in range(n_epochs): for e in range(n_epochs):
print("epoch", e) print("epoch", e)
self.pm.fit(X = self.sdm.X[:max_size], y = self.sdm.y[:max_size]) self.pm.fit(X = self.sdm.X[:max_size], y = self.sdm.y[:max_size])
pred, yt = self.test() pred, yt = self.test()
mean_squared_error = ((pred - yt)**2).mean(axis=0) mean_squared_error = ((pred - yt)**2).mean(axis=0)
print("#" + str(e) + ": validation loss: ", mean_squared_error, "scalar: ", np.mean(mean_squared_error)) print("#" + str(e) + ": validation loss: ", mean_squared_error, "scalar: ", np.mean(mean_squared_error))
self.val.append(np.mean(mean_squared_error))
plt.figure(figsize=(10,5))
plt.plot(self.val)
plt.savefig("val_error" + str(datetime.datetime.now()) + ".png", bbox_inches='tight')
plt.show()
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):