based on ex and notes by Allison Parish Original text is the wikipedia entry for truth
note: textgenrnn is less effective when training on/predicting longer sequences (> 200 characters). Likewise textgenrnn is less effective when training on/predicting texts with very disparate grammatical styles.
!conda install -y keras
Solving environment: done ## Package Plan ## environment location: /Users/SebastianRev1/anaconda3 added / updated specs: - keras The following packages will be downloaded: package | build ---------------------------|----------------- numpy-1.12.1 | py36h8871d66_1 3.6 MB ca-certificates-2018.03.07 | 0 124 KB keras-2.1.5 | py36_0 490 KB certifi-2018.1.18 | py36_0 143 KB protobuf-3.5.1 | py36h0a44026_0 589 KB tensorflow-1.1.0 | np112py36_0 23.6 MB openssl-1.0.2o | h26aff7b_0 3.4 MB libprotobuf-3.5.1 | h2cd40f5_0 4.0 MB numba-0.37.0 |np112py36hb493f12_0 2.3 MB ------------------------------------------------------------ Total: 38.3 MB The following NEW packages will be INSTALLED: keras: 2.1.5-py36_0 libprotobuf: 3.5.1-h2cd40f5_0 protobuf: 3.5.1-py36h0a44026_0 tensorflow: 1.1.0-np112py36_0 The following packages will be UPDATED: ca-certificates: 2017.08.26-ha1e5d58_0 --> 2018.03.07-0 certifi: 2017.7.27.1-py36hd973bb6_0 --> 2018.1.18-py36_0 numba: 0.37.0-np114py36h210bcc1_0 --> 0.37.0-np112py36hb493f12_0 openssl: 1.0.2l-h57f3a61_2 --> 1.0.2o-h26aff7b_0 The following packages will be DOWNGRADED: numpy: 1.14.2-py36ha9ae307_1 --> 1.12.1-py36h8871d66_1 Downloading and Extracting Packages numpy 1.12.1: ########################################################## | 100% ca-certificates 2018.03.07: ############################################ | 100% keras 2.1.5: ########################################################### | 100% certifi 2018.1.18: ##################################################### | 100% protobuf 3.5.1: ######################################################## | 100% tensorflow 1.1.0: ###################################################### | 100% openssl 1.0.2o: ######################################################## | 100% libprotobuf 3.5.1: ##################################################### | 100% numba 0.37.0: ########################################################## | 100% Preparing transaction: done Verifying transaction: done Executing transaction: done
!pip install textgenrnn
Collecting textgenrnn Downloading textgenrnn-0.1.1.tar.gz (777kB) 100% |████████████████████████████████| 778kB 1.5MB/s ta 0:00:011 Requirement already satisfied: tensorflow in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from textgenrnn) Requirement already satisfied: keras in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from textgenrnn) Requirement already satisfied: h5py in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from textgenrnn) Requirement already satisfied: werkzeug>=0.11.10 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from tensorflow->textgenrnn) Requirement already satisfied: six>=1.10.0 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from tensorflow->textgenrnn) Requirement already satisfied: protobuf>=3.2.0 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from tensorflow->textgenrnn) Requirement already satisfied: numpy>=1.11.0 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from tensorflow->textgenrnn) Requirement already satisfied: wheel>=0.26 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from tensorflow->textgenrnn) Requirement already satisfied: scipy>=0.14 in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from keras->textgenrnn) Requirement already satisfied: pyyaml in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from keras->textgenrnn) Requirement already satisfied: setuptools in /Users/SebastianRev1/anaconda3/lib/python3.6/site-packages (from protobuf>=3.2.0->tensorflow->textgenrnn) Building wheels for collected packages: textgenrnn Running setup.py bdist_wheel for textgenrnn ... done Stored in directory: /Users/SebastianRev1/Library/Caches/pip/wheels/59/b1/4a/b5ee074f89a4fb3632930705658c28ba38cfacd38f29bc1340 Successfully built textgenrnn Installing collected packages: textgenrnn Successfully installed textgenrnn-0.1.1
from textgenrnn import textgenrnn
Using TensorFlow backend.
textgen = textgenrnn()
textgen.generate()
The super complete the body the first party of the star to the star consequences and some of the street and the star world of the sub in the band to a look at the star to the signed of the promised
num_epochs =more better, specially shorter texts
textgen.train_on_texts(open("text_examples/truth.txt").readlines(), num_epochs=10)
Epoch 1/10 3055/3055 [==============================] - 3s 1ms/step - loss: 1.5610 Epoch 2/10 3055/3055 [==============================] - 3s 1ms/step - loss: 1.2773 Epoch 3/10 3055/3055 [==============================] - 3s 994us/step - loss: 1.1380 Epoch 4/10 3055/3055 [==============================] - 3s 1ms/step - loss: 1.0471 Epoch 5/10 3055/3055 [==============================] - 4s 1ms/step - loss: 0.9824 Epoch 6/10 3055/3055 [==============================] - 3s 1ms/step - loss: 0.9310 Epoch 7/10 3055/3055 [==============================] - 3s 1ms/step - loss: 0.8931 Epoch 8/10 3055/3055 [==============================] - 3s 1ms/step - loss: 0.8623 Epoch 9/10 3055/3055 [==============================] - 4s 1ms/step - loss: 0.8389 Epoch 10/10 3055/3055 [==============================] - 3s 1ms/step - loss: 0.8214
textgen.generate(5,temperature=.7,prefix='fly')
flying the concept of last inquiry or contential concept at the dermative of truth. Truth of the infame on the concept and truth of suich and need to truth when the debuty of Truth College for truth flying are meaning the mean and basic would another these or life in the original Greechaire that an our unnevegate in the truth and lit and blaceplay in the original most of truth is being from the flying take as what was always by the concept until the debate. I done a discussion from the fact, the deried ago of antilitience essence vacainita and truth of secondary of meane being a nature and flyes in the reality in term itsers in the concept of a truth to be debated to our original or original by the conferetion of truth of the concept of trutheer died for truth, and truth on and essenc flyes who take the reported jather take a human fact, and discovering tradential beet to be elitisms or faith of infirmed facidly offiniously familin conception, and essence in a watch of truth as m
poem = textgen.generate(10, temperature=0.8, return_as_list=True)
for line in poem:
print(line.strip())
Are term by the truth is term to by the view and contextion as he can we am faighters in how to truth summon and also metaphysically false, than the divinion tradition in the concept, what is exciti Pictorication is wirepessible that an election: "As get a "conceptics of until and earth" factions as Britas Greeker is a faith, the according to another ebs concept which include would be plays a c Many were hair opena conception to be theories, and discumed grandaries what or life up may is another to detain." Let us an original fauth-play, original meaning, or himself, the election to relai Gordary a things or anceiring at Truth is more faith capances of this faith Truth to be explainesed to truth aporteag togethon and calling in and include that we an often be applying to be yet, the back of truth, and the concept, that the development in a relation on truth, Or ancertaging of being inquiry .. Peirce time that truth as lies ob faith as some faith or voted or foundative, a reasession train to defend, and the selfies. I fan a Helbsolo as the dermation caturn or also Friedrive and the emojias or mean in idea essence, it view. http://abcn.ws/2tg0HL I am things are the score of being a youtubest used to be explained as an opported our and what is relationshorts to oceas that year ofter and even we another that truth is notice, an thousand, the What dossooss of Praisoull concept as readly term truth to Pessuilty are sub or meaning this each of alson, and everyday, Truth still truth, include of truth as belief to one astross esting the fait
poem = textgen.generate(10, temperature=0.5, return_as_list=True)
for line in poem:
print(line.strip())
Truth is 'De corresponden by the concept of friever a dependence leaves than sciences, what congeting to an inding than to and the revealing take tradit, factual faithlas takene. Many human activiti Some manner of some manner of essential relation to human practices words are a metaphysical being in the fire term veritas. Pragmatists like C. S. Peirce take to refer to an idea of truth as stoniogn which what is termed a concept or through, where its nature as anaman nature as far as it could profitably go: "The opinio Various theories and views of truth can even false that an olame holding this be explained in a late, bring a being a based ard terms that an ancient or theories as correctness is a later derivation Truth is most often used to refer to an indepreding concept of truth as what is a "truth, what is what human, undervivitived by truth is subjective hote for the concept, where out to be be usually i Various theories and views of truth continue to be debated among standar, suggested and derivative or secondary and derivative. According for inquitite truth" as the concept of truth is being to mea Some hall absolute inquiry would time to be explained in anyone has discovers theat theory or anti-metaphysicians stone in the truth tracer that Truth is metaphys in Schithole lit fact or %reaman ph Friedrich Nietzsche famously suggested that an ancient, what human activities depend upon the concept, where its pleview, who collecture. Commonly, truth is viewed as the correspondence of modern co
textgen.reset()
One of my biggest challenges is that this rrn method works well only with language (english...) That is becasue english language is very felxible, even when the message doesn't make sense it can still be displayed. Even when the word doesn't exist you can still write it.
I guess what I would be interested is to use something like this but with other language, like an image, or a 3d model, or a website. But the challenge is that all this things have a very strict syntax and a small error will make the entity invalid.
import random
list_of_words=['tech','apple','google','FaceBook']
techTruth=[]
for word in list_of_words:
temp=random.random()
if(temp>.6):
temp=random.random()
line=(textgen.generate(temperature=temp,prefix=word,return_as_list=True));
techTruth.append(line)
print(line)
['tech truth of the original Barts of truth the truth concept of truth famously being a income food to take. Don\'t take these science of later, which is toq and the score" is still you are faith and t'] ['apple of the faith or truth to be a later of truth in the concept, and the concept of truth of truth in the truth of truth is a later of truth is a later of truth is truticed to be debated and every'] ['googles of truth to an idea of truth to an earth and relative truth.\n\nIt relative one of truth of assumes and faith, an original the concept of truth as bashering to an intellectual faith on such in'] ['FaceBook and Suggesten faith truth to mean the concept, and the resting and truth is a concept, which to be original or truth of the concept of truth to an including and truth of truth meaning to be']
“The self is a relation which relates itself to its own self, or it is that in the relation the relation relates itself to its own self; the self is not the relation but the relation relates itself to its own self.”
** let me change the input corpus **
textgen.reset()
textgen.train_on_texts(open("text_examples/truthShort.txt").readlines(), num_epochs=20)
Epoch 1/20 1865/1865 [==============================] - 2s 1ms/step - loss: 1.5918 Epoch 2/20 1865/1865 [==============================] - 2s 1ms/step - loss: 1.2825 Epoch 3/20 1865/1865 [==============================] - 2s 1ms/step - loss: 1.1169 Epoch 4/20 1865/1865 [==============================] - 2s 1ms/step - loss: 1.0119 Epoch 5/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.9380 Epoch 6/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.8783 Epoch 7/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.8302 Epoch 8/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.7872 Epoch 9/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.7543 Epoch 10/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.7247 Epoch 11/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6974 Epoch 12/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6733 Epoch 13/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6530 Epoch 14/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6356 Epoch 15/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6198 Epoch 16/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.6070 Epoch 17/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.5962 Epoch 18/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.5868 Epoch 19/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.5790 Epoch 20/20 1865/1865 [==============================] - 2s 1ms/step - loss: 0.5735
import random
list_of_words=['Technology','Apple','Google','Facebook','Amazon']
techTruth=[]
for word in list_of_words:
temp=random.random()
#weighting down the chance for something to crazy
if(temp>.4):
temp=random.random()
line=(textgen.generate(temperature=temp,prefix=word,return_as_list=True));
techTruth.append(line)
print(line)
['Technology and the concept of truth as debated that the concept of truth is a logical faith, that the concept of truth as a concept of truth is a logical term of truth in the concept of truth is a l'] ['Applegies open as a nature at the revealing which is a "truth"'] ["Google of truth are termed for truth that a lit 'Lation. The entire was also conventine' of conception and fact methoo indipal veritas. Beying a crated time as a faith who was nuass the essentis int"] ['Facebook and was among kid has a litting and of truth in the contection for the concept, and that being what its are one in the original manch as the concept of truth used to debated the method than'] ['Amazon of truth is a faith the concept of truth in the concept of truth in the concept, and the concept of truth in the concept of truth is a later of truth in the concept, which is a logical faith ']
This is all for now... I find the idea exciting althought the execution a little limmiting. I guess this is the problem of trying to use tools that we have no idea how they work or how to change them