텍스트 로드하기

pip install "tensorflow-text==2.8.*"

import collections
import pathlib

import tensorflow as tf

from tensorflow.keras import layers
from tensorflow.keras import losses
from tensorflow.keras import utils
from tensorflow.keras.layers import TextVectorization

import tensorflow_datasets as tfds
import tensorflow_text as tf_text

data_url = 'https://storage.googleapis.com/download.tensorflow.org/data/stack_overflow_16k.tar.gz'

dataset_dir = utils.get_file(
    origin=data_url,
    untar=True,
    cache_dir='stack_overflow',
    cache_subdir='')

dataset_dir = pathlib.Path(dataset_dir).parent

Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/stack_overflow_16k.tar.gz
6053888/6053168 [==============================] - 0s 0us/step
6062080/6053168 [==============================] - 0s 0us/step

list(dataset_dir.iterdir())

[PosixPath('/tmp/.keras/test'),
 PosixPath('/tmp/.keras/train'),
 PosixPath('/tmp/.keras/README.md'),
 PosixPath('/tmp/.keras/stack_overflow_16k.tar.gz')]

train_dir = dataset_dir/'train'
list(train_dir.iterdir())

[PosixPath('/tmp/.keras/train/csharp'),
 PosixPath('/tmp/.keras/train/javascript'),
 PosixPath('/tmp/.keras/train/python'),
 PosixPath('/tmp/.keras/train/java')]

sample_file = train_dir/'python/1755.txt'

with open(sample_file) as f:
  print(f.read())

why does this blank program print true x=true.def stupid():.    x=false.stupid().print x

train/
...csharp/
......1.txt
......2.txt
...java/
......1.txt
......2.txt
...javascript/
......1.txt
......2.txt
...python/
......1.txt
......2.txt

batch_size = 32
seed = 42

raw_train_ds = utils.text_dataset_from_directory(
    train_dir,
    batch_size=batch_size,
    validation_split=0.2,
    subset='training',
    seed=seed)

Found 8000 files belonging to 4 classes.
Using 6400 files for training.

for text_batch, label_batch in raw_train_ds.take(1):
  for i in range(10):
    print("Question: ", text_batch.numpy()[i])
    print("Label:", label_batch.numpy()[i])

Question:  b'"my tester is going to the wrong constructor i am new to programming so if i ask a question that can be easily fixed, please forgive me. my program has a tester class with a main. when i send that to my regularpolygon class, it sends it to the wrong constructor. i have two constructors. 1 without perameters..public regularpolygon().    {.       mynumsides = 5;.       mysidelength = 30;.    }//end default constructor...and my second, with perameters. ..public regularpolygon(int numsides, double sidelength).    {.        mynumsides = numsides;.        mysidelength = sidelength;.    }// end constructor...in my tester class i have these two lines:..regularpolygon shape = new regularpolygon(numsides, sidelength);.        shape.menu();...numsides and sidelength were declared and initialized earlier in the testing class...so what i want to happen, is the tester class sends numsides and sidelength to the second constructor and use it in that class. but it only uses the default constructor, which therefor ruins the whole rest of the program. can somebody help me?..for those of you who want to see more of my code: here you go..public double vertexangle().    {.        system.out.println(""the vertex angle method: "" + mynumsides);// prints out 5.        system.out.println(""the vertex angle method: "" + mysidelength); // prints out 30..        double vertexangle;.        vertexangle = ((mynumsides - 2.0) / mynumsides) * 180.0;.        return vertexangle;.    }//end method vertexangle..public void menu().{.    system.out.println(mynumsides); // prints out what the user puts in.    system.out.println(mysidelength); // prints out what the user puts in.    gotographic();.    calcr(mynumsides, mysidelength);.    calcr(mynumsides, mysidelength);.    print(); .}// end menu...this is my entire tester class:..public static void main(string[] arg).{.    int numsides;.    double sidelength;.    scanner keyboard = new scanner(system.in);..    system.out.println(""welcome to the regular polygon program!"");.    system.out.println();..    system.out.print(""enter the number of sides of the polygon ==> "");.    numsides = keyboard.nextint();.    system.out.println();..    system.out.print(""enter the side length of each side ==> "");.    sidelength = keyboard.nextdouble();.    system.out.println();..    regularpolygon shape = new regularpolygon(numsides, sidelength);.    shape.menu();.}//end main...for testing it i sent it numsides 4 and sidelength 100."\n'
Label: 1
Question:  b'"blank code slow skin detection this code changes the color space to lab and using a threshold finds the skin area of an image. but it\'s ridiculously slow. i don\'t know how to make it faster ?    ..from colormath.color_objects import *..def skindetection(img, treshold=80, color=[255,20,147]):..    print img.shape.    res=img.copy().    for x in range(img.shape[0]):.        for y in range(img.shape[1]):.            rgbimg=rgbcolor(img[x,y,0],img[x,y,1],img[x,y,2]).            labimg=rgbimg.convert_to(\'lab\', debug=false).            if (labimg.lab_l > treshold):.                res[x,y,:]=color.            else: .                res[x,y,:]=img[x,y,:]..    return res"\n'
Label: 3
Question:  b'"option and validation in blank i want to add a new option on my system where i want to add two text files, both rental.txt and customer.txt. inside each text are id numbers of the customer, the videotape they need and the price...i want to place it as an option on my code. right now i have:...add customer.rent return.view list.search.exit...i want to add this as my sixth option. say for example i ordered a video, it would display the price and would let me confirm the price and if i am going to buy it or not...here is my current code:..  import blank.io.*;.    import blank.util.arraylist;.    import static blank.lang.system.out;..    public class rentalsystem{.    static bufferedreader input = new bufferedreader(new inputstreamreader(system.in));.    static file file = new file(""file.txt"");.    static arraylist<string> list = new arraylist<string>();.    static int rows;..    public static void main(string[] args) throws exception{.        introduction();.        system.out.print(""nn"");.        login();.        system.out.print(""nnnnnnnnnnnnnnnnnnnnnn"");.        introduction();.        string repeat;.        do{.            loadfile();.            system.out.print(""nwhat do you want to do?nn"");.            system.out.print(""n                    - - - - - - - - - - - - - - - - - - - - - - -"");.            system.out.print(""nn                    |     1. add customer    |   2. rent return |n"");.            system.out.print(""n                    - - - - - - - - - - - - - - - - - - - - - - -"");.            system.out.print(""nn                    |     3. view list       |   4. search      |n"");.            system.out.print(""n                    - - - - - - - - - - - - - - - - - - - - - - -"");.            system.out.print(""nn                                             |   5. exit        |n"");.            system.out.print(""n                                              - - - - - - - - - -"");.            system.out.print(""nnchoice:"");.            int choice = integer.parseint(input.readline());.            switch(choice){.                case 1:.                    writedata();.                    break;.                case 2:.                    rentdata();.                    break;.                case 3:.                    viewlist();.                    break;.                case 4:.                    search();.                    break;.                case 5:.                    system.out.println(""goodbye!"");.                    system.exit(0);.                default:.                    system.out.print(""invalid choice: "");.                    break;.            }.            system.out.print(""ndo another task? [y/n] "");.            repeat = input.readline();.        }while(repeat.equals(""y""));..        if(repeat!=""y"") system.out.println(""ngoodbye!"");..    }..    public static void writedata() throws exception{.        system.out.print(""nname: "");.        string cname = input.readline();.        system.out.print(""address: "");.        string add = input.readline();.        system.out.print(""phone no.: "");.        string pno = input.readline();.        system.out.print(""rental amount: "");.        string ramount = input.readline();.        system.out.print(""tapenumber: "");.        string tno = input.readline();.        system.out.print(""title: "");.        string title = input.readline();.        system.out.print(""date borrowed: "");.        string dborrowed = input.readline();.        system.out.print(""due date: "");.        string ddate = input.readline();.        createline(cname, add, pno, ramount,tno, title, dborrowed, ddate);.        rentdata();.    }..    public static void createline(string name, string address, string phone , string rental, string tapenumber, string title, string borrowed, string due) throws exception{.        filewriter fw = new filewriter(file, true);.        fw.write(""nname: ""+name + ""naddress: "" + address +""nphone no.: ""+ phone+""nrentalamount: ""+rental+""ntape no.: ""+ tapenumber+""ntitle: ""+ title+""ndate borrowed: ""+borrowed +""ndue date: ""+ due+"":rn"");.        fw.close();.    }..    public static void loadfile() throws exception{.        try{.            list.clear();.            fileinputstream fstream = new fileinputstream(file);.            bufferedreader br = new bufferedreader(new inputstreamreader(fstream));.            rows = 0;.            while( br.ready()).            {.                list.add(br.readline());.                rows++;.            }.            br.close();.        } catch(exception e){.            system.out.println(""list not yet loaded."");.        }.    }..    public static void viewlist(){.        system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        system.out.print("" |list of all costumers|"");.        system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        for(int i = 0; i <rows; i++){.            system.out.println(list.get(i));.        }.    }.        public static void rentdata()throws exception.    {   system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        system.out.print("" |rent data list|"");.        system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        system.out.print(""nenter customer name: "");.        string cname = input.readline();.        system.out.print(""date borrowed: "");.        string dborrowed = input.readline();.        system.out.print(""due date: "");.        string ddate = input.readline();.        system.out.print(""return date: "");.        string rdate = input.readline();.        system.out.print(""rent amount: "");.        string ramount = input.readline();..        system.out.print(""you pay:""+ramount);...    }.    public static void search()throws exception.    {   system.out.print(""n~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        system.out.print("" |search costumers|"");.        system.out.print(""~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~"");.        system.out.print(""nenter costumer name: "");.        string cname = input.readline();.        boolean found = false;..        for(int i=0; i < rows; i++){.            string temp[] = list.get(i).split("","");..            if(cname.equals(temp[0])){.            system.out.println(""search result:nyou are "" + temp[0] + "" from "" + temp[1] + "".""+ temp[2] + "".""+ temp[3] + "".""+ temp[4] + "".""+ temp[5] + "" is "" + temp[6] + "".""+ temp[7] + "" is "" + temp[8] + ""."");.                found = true;.            }.        }..        if(!found){.            system.out.print(""no results."");.        }..    }..        public static boolean evaluate(string uname, string pass){.        if (uname.equals(""admin"")&&pass.equals(""12345"")) return true;.        else return false;.    }..    public static string login()throws exception{.        bufferedreader input=new bufferedreader(new inputstreamreader(system.in));.        int counter=0;.        do{.            system.out.print(""username:"");.            string uname =input.readline();.            system.out.print(""password:"");.            string pass =input.readline();..            boolean accept= evaluate(uname,pass);..            if(accept){.                break;.                }else{.                    system.out.println(""incorrect username or password!"");.                    counter ++;.                    }.        }while(counter<3);..            if(counter !=3) return ""login successful"";.            else return ""login failed"";.            }.        public static void introduction() throws exception{..        system.out.println(""                  - - - - - - - - - - - - - - - - - - - - - - - - -"");.        system.out.println(""                  !                  r e n t a l                  !"");.        system.out.println(""                   ! ~ ~ ~ ~ ~ !  =================  ! ~ ~ ~ ~ ~ !"");.        system.out.println(""                  !                  s y s t e m                  !"");.        system.out.println(""                  - - - - - - - - - - - - - - - - - - - - - - - - -"");.        }..}"\n'
Label: 1
Question:  b'"exception: dynamic sql generation for the updatecommand is not supported against a selectcommand that does not return any key i dont know what is the problem this my code : ..string nomtable;..datatable listeetablissementtable = new datatable();.datatable listeinteretstable = new datatable();.dataset ds = new dataset();.sqldataadapter da;.sqlcommandbuilder cmdb;..private void listeinterets_click(object sender, eventargs e).{.    nomtable = ""listeinteretstable"";.    d.cnx.open();.    da = new sqldataadapter(""select nome from offices"", d.cnx);.    ds = new dataset();.    da.fill(ds, nomtable);.    datagridview1.datasource = ds.tables[nomtable];.}..private void sauvgarder_click(object sender, eventargs e).{.    d.cnx.open();.    cmdb = new sqlcommandbuilder(da);.    da.update(ds, nomtable);.    d.cnx.close();.}"\n'
Label: 0
Question:  b'"parameter with question mark and super in blank, i\'ve come across a method that is formatted like this:..public final subscription subscribe(final action1<? super t> onnext, final action1<throwable> onerror) {.}...in the first parameter, what does the question mark and super mean?"\n'
Label: 1
Question:  b'call two objects wsdl the first time i got a very strange wsdl. ..i would like to call the object (interface - invoicecheck_out) do you know how?....i would like to call the object (variable) do you know how?..try to call (it`s ok)....try to call (how call this?)\n'
Label: 0
Question:  b"how to correctly make the icon for systemtray in blank using icon sizes of any dimension for systemtray doesn't look good overall. .what is the correct way of making icons for windows system tray?..screenshots: http://imgur.com/zsibwn9..icon: http://imgur.com/vsh4zo8\n"
Label: 0
Question:  b'"is there a way to check a variable that exists in a different script than the original one? i\'m trying to check if a variable, which was previously set to true in 2.py in 1.py, as 1.py is only supposed to continue if the variable is true...2.py..import os..completed = false..#some stuff here..completed = true...1.py..import 2 ..if completed == true.   #do things...however i get a syntax error at ..if completed == true"\n'
Label: 3
Question:  b'"blank control flow i made a number which asks for 2 numbers with blank and responds with  the corresponding message for the case. how come it doesnt work  for the second number ? .regardless what i enter for the second number , i am getting the message ""your number is in the range 0-10""...using system;.using system.collections.generic;.using system.linq;.using system.text;..namespace consoleapplication1.{.    class program.    {.        static void main(string[] args).        {.            string myinput;  // declaring the type of the variables.            int myint;..            string number1;.            int number;...            console.writeline(""enter a number"");.            myinput = console.readline(); //muyinput is a string  which is entry input.            myint = int32.parse(myinput); // myint converts the string into an integer..            if (myint > 0).                console.writeline(""your number {0} is greater than zero."", myint);.            else if (myint < 0).                console.writeline(""your number {0} is  less  than zero."", myint);.            else.                console.writeline(""your number {0} is equal zero."", myint);..            console.writeline(""enter another number"");.            number1 = console.readline(); .            number = int32.parse(myinput); ..            if (number < 0 || number == 0).                console.writeline(""your number {0} is  less  than zero or equal zero."", number);.            else if (number > 0 && number <= 10).                console.writeline(""your number {0} is  in the range from 0 to 10."", number);.            else.                console.writeline(""your number {0} is greater than 10."", number);..            console.writeline(""enter another number"");..        }.    }    .}"\n'
Label: 0
Question:  b'"credentials cannot be used for ntlm authentication i am getting org.apache.commons.httpclient.auth.invalidcredentialsexception: credentials cannot be used for ntlm authentication: exception in eclipse..whether it is possible mention eclipse to take system proxy settings directly?..public class httpgetproxy {.    private static final string proxy_host = ""proxy.****.com"";.    private static final int proxy_port = 6050;..    public static void main(string[] args) {.        httpclient client = new httpclient();.        httpmethod method = new getmethod(""https://kodeblank.org"");..        hostconfiguration config = client.gethostconfiguration();.        config.setproxy(proxy_host, proxy_port);..        string username = ""*****"";.        string password = ""*****"";.        credentials credentials = new usernamepasswordcredentials(username, password);.        authscope authscope = new authscope(proxy_host, proxy_port);..        client.getstate().setproxycredentials(authscope, credentials);..        try {.            client.executemethod(method);..            if (method.getstatuscode() == httpstatus.sc_ok) {.                string response = method.getresponsebodyasstring();.                system.out.println(""response = "" + response);.            }.        } catch (ioexception e) {.            e.printstacktrace();.        } finally {.            method.releaseconnection();.        }.    }.}...exception:...  dec 08, 2017 1:41:39 pm .          org.apache.commons.httpclient.auth.authchallengeprocessor selectauthscheme.         info: ntlm authentication scheme selected.       dec 08, 2017 1:41:39 pm org.apache.commons.httpclient.httpmethoddirector executeconnect.         severe: credentials cannot be used for ntlm authentication: .           org.apache.commons.httpclient.usernamepasswordcredentials.           org.apache.commons.httpclient.auth.invalidcredentialsexception: credentials .         cannot be used for ntlm authentication: .        enter code here .          org.apache.commons.httpclient.usernamepasswordcredentials.      at org.apache.commons.httpclient.auth.ntlmscheme.authenticate(ntlmscheme.blank:332).        at org.apache.commons.httpclient.httpmethoddirector.authenticateproxy(httpmethoddirector.blank:320).      at org.apache.commons.httpclient.httpmethoddirector.executeconnect(httpmethoddirector.blank:491).      at org.apache.commons.httpclient.httpmethoddirector.executewithretry(httpmethoddirector.blank:391).      at org.apache.commons.httpclient.httpmethoddirector.executemethod(httpmethoddirector.blank:171).      at org.apache.commons.httpclient.httpclient.executemethod(httpclient.blank:397).      at org.apache.commons.httpclient.httpclient.executemethod(httpclient.blank:323).      at httpgetproxy.main(httpgetproxy.blank:31).  dec 08, 2017 1:41:39 pm org.apache.commons.httpclient.httpmethoddirector processproxyauthchallenge.  info: failure authenticating with ntlm @proxy.****.com:6050"\n'
Label: 1

for i, label in enumerate(raw_train_ds.class_names):
  print("Label", i, "corresponds to", label)

Label 0 corresponds to csharp
Label 1 corresponds to java
Label 2 corresponds to javascript
Label 3 corresponds to python

# Create a validation set.
raw_val_ds = utils.text_dataset_from_directory(
    train_dir,
    batch_size=batch_size,
    validation_split=0.2,
    subset='validation',
    seed=seed)

Found 8000 files belonging to 4 classes.
Using 1600 files for validation.

test_dir = dataset_dir/'test'

# Create a test set.
raw_test_ds = utils.text_dataset_from_directory(
    test_dir,
    batch_size=batch_size)

Found 8000 files belonging to 4 classes.

VOCAB_SIZE = 10000

binary_vectorize_layer = TextVectorization(
    max_tokens=VOCAB_SIZE,
    output_mode='binary')

MAX_SEQUENCE_LENGTH = 250

int_vectorize_layer = TextVectorization(
    max_tokens=VOCAB_SIZE,
    output_mode='int',
    output_sequence_length=MAX_SEQUENCE_LENGTH)

# Make a text-only dataset (without labels), then call `TextVectorization.adapt`.
train_text = raw_train_ds.map(lambda text, labels: text)
binary_vectorize_layer.adapt(train_text)
int_vectorize_layer.adapt(train_text)

def binary_vectorize_text(text, label):
  text = tf.expand_dims(text, -1)
  return binary_vectorize_layer(text), label

def int_vectorize_text(text, label):
  text = tf.expand_dims(text, -1)
  return int_vectorize_layer(text), label

# Retrieve a batch (of 32 reviews and labels) from the dataset.
text_batch, label_batch = next(iter(raw_train_ds))
first_question, first_label = text_batch[0], label_batch[0]
print("Question", first_question)
print("Label", first_label)

Question tf.Tensor(b'"what is the difference between these two ways to create an element? var a = document.createelement(\'div\');..a.id = ""mydiv"";...and..var a = document.createelement(\'div\').id = ""mydiv"";...what is the difference between them such that the first one works and the second one doesn\'t?"\n', shape=(), dtype=string)
Label tf.Tensor(2, shape=(), dtype=int32)

print("'binary' vectorized question:",
      binary_vectorize_text(first_question, first_label)[0])

'binary' vectorized question: tf.Tensor([[1. 1. 0. ... 0. 0. 0.]], shape=(1, 10000), dtype=float32)

print("'int' vectorized question:",
      int_vectorize_text(first_question, first_label)[0])

'int' vectorized question: tf.Tensor(
[[ 55   6   2 410 211 229 121 895   4 124  32 245  43   5   1   1   5   1
    1   6   2 410 211 191 318  14   2  98  71 188   8   2 199  71 178   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0
    0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]], shape=(1, 250), dtype=int64)

print("1289 ---> ", int_vectorize_layer.get_vocabulary()[1289])
print("313 ---> ", int_vectorize_layer.get_vocabulary()[313])
print("Vocabulary size: {}".format(len(int_vectorize_layer.get_vocabulary())))

1289 --->  roman
313 --->  source
Vocabulary size: 10000

binary_train_ds = raw_train_ds.map(binary_vectorize_text)
binary_val_ds = raw_val_ds.map(binary_vectorize_text)
binary_test_ds = raw_test_ds.map(binary_vectorize_text)

int_train_ds = raw_train_ds.map(int_vectorize_text)
int_val_ds = raw_val_ds.map(int_vectorize_text)
int_test_ds = raw_test_ds.map(int_vectorize_text)

AUTOTUNE = tf.data.AUTOTUNE

def configure_dataset(dataset):
  return dataset.cache().prefetch(buffer_size=AUTOTUNE)

binary_train_ds = configure_dataset(binary_train_ds)
binary_val_ds = configure_dataset(binary_val_ds)
binary_test_ds = configure_dataset(binary_test_ds)

int_train_ds = configure_dataset(int_train_ds)
int_val_ds = configure_dataset(int_val_ds)
int_test_ds = configure_dataset(int_test_ds)

binary_model = tf.keras.Sequential([layers.Dense(4)])

binary_model.compile(
    loss=losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer='adam',
    metrics=['accuracy'])

history = binary_model.fit(
    binary_train_ds, validation_data=binary_val_ds, epochs=10)

Epoch 1/10
200/200 [==============================] - 2s 5ms/step - loss: 1.1217 - accuracy: 0.6442 - val_loss: 0.9182 - val_accuracy: 0.7837
Epoch 2/10
200/200 [==============================] - 1s 3ms/step - loss: 0.7805 - accuracy: 0.8181 - val_loss: 0.7533 - val_accuracy: 0.8056
Epoch 3/10
200/200 [==============================] - 1s 3ms/step - loss: 0.6291 - accuracy: 0.8609 - val_loss: 0.6673 - val_accuracy: 0.8131
Epoch 4/10
200/200 [==============================] - 1s 3ms/step - loss: 0.5355 - accuracy: 0.8861 - val_loss: 0.6135 - val_accuracy: 0.8238
Epoch 5/10
200/200 [==============================] - 1s 3ms/step - loss: 0.4694 - accuracy: 0.9031 - val_loss: 0.5767 - val_accuracy: 0.8344
Epoch 6/10
200/200 [==============================] - 1s 3ms/step - loss: 0.4191 - accuracy: 0.9150 - val_loss: 0.5499 - val_accuracy: 0.8381
Epoch 7/10
200/200 [==============================] - 1s 3ms/step - loss: 0.3788 - accuracy: 0.9270 - val_loss: 0.5296 - val_accuracy: 0.8394
Epoch 8/10
200/200 [==============================] - 1s 3ms/step - loss: 0.3454 - accuracy: 0.9364 - val_loss: 0.5139 - val_accuracy: 0.8400
Epoch 9/10
200/200 [==============================] - 1s 3ms/step - loss: 0.3171 - accuracy: 0.9411 - val_loss: 0.5016 - val_accuracy: 0.8406
Epoch 10/10
200/200 [==============================] - 1s 3ms/step - loss: 0.2927 - accuracy: 0.9483 - val_loss: 0.4917 - val_accuracy: 0.8419

def create_model(vocab_size, num_labels):
  model = tf.keras.Sequential([
      layers.Embedding(vocab_size, 64, mask_zero=True),
      layers.Conv1D(64, 5, padding="valid", activation="relu", strides=2),
      layers.GlobalMaxPooling1D(),
      layers.Dense(num_labels)
  ])
  return model

# `vocab_size` is `VOCAB_SIZE + 1` since `0` is used additionally for padding.
int_model = create_model(vocab_size=VOCAB_SIZE + 1, num_labels=4)
int_model.compile(
    loss=losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer='adam',
    metrics=['accuracy'])
history = int_model.fit(int_train_ds, validation_data=int_val_ds, epochs=5)

Epoch 1/5
200/200 [==============================] - 3s 4ms/step - loss: 1.1294 - accuracy: 0.5203 - val_loss: 0.7556 - val_accuracy: 0.6975
Epoch 2/5
200/200 [==============================] - 1s 4ms/step - loss: 0.6195 - accuracy: 0.7614 - val_loss: 0.5407 - val_accuracy: 0.7950
Epoch 3/5
200/200 [==============================] - 1s 4ms/step - loss: 0.3703 - accuracy: 0.8869 - val_loss: 0.4717 - val_accuracy: 0.8231
Epoch 4/5
200/200 [==============================] - 1s 4ms/step - loss: 0.2032 - accuracy: 0.9527 - val_loss: 0.4726 - val_accuracy: 0.8200
Epoch 5/5
200/200 [==============================] - 1s 4ms/step - loss: 0.1002 - accuracy: 0.9822 - val_loss: 0.4988 - val_accuracy: 0.8169

print("Linear model on binary vectorized data:")
print(binary_model.summary())

Linear model on binary vectorized data:
Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense (Dense)               (None, 4)                 40004     
                                                                 
=================================================================
Total params: 40,004
Trainable params: 40,004
Non-trainable params: 0
_________________________________________________________________
None

print("ConvNet model on int vectorized data:")
print(int_model.summary())

ConvNet model on int vectorized data:
Model: "sequential_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 embedding (Embedding)       (None, None, 64)          640064    
                                                                 
 conv1d (Conv1D)             (None, None, 64)          20544     
                                                                 
 global_max_pooling1d (Globa  (None, 64)               0         
 lMaxPooling1D)                                                  
                                                                 
 dense_1 (Dense)             (None, 4)                 260       
                                                                 
=================================================================
Total params: 660,868
Trainable params: 660,868
Non-trainable params: 0
_________________________________________________________________
None

binary_loss, binary_accuracy = binary_model.evaluate(binary_test_ds)
int_loss, int_accuracy = int_model.evaluate(int_test_ds)

print("Binary model accuracy: {:2.2%}".format(binary_accuracy))
print("Int model accuracy: {:2.2%}".format(int_accuracy))

250/250 [==============================] - 1s 3ms/step - loss: 0.5180 - accuracy: 0.8164
250/250 [==============================] - 1s 2ms/step - loss: 0.5057 - accuracy: 0.8150
Binary model accuracy: 81.64%
Int model accuracy: 81.50%

export_model = tf.keras.Sequential(
    [binary_vectorize_layer, binary_model,
     layers.Activation('sigmoid')])

export_model.compile(
    loss=losses.SparseCategoricalCrossentropy(from_logits=False),
    optimizer='adam',
    metrics=['accuracy'])

# Test it with `raw_test_ds`, which yields raw strings
loss, accuracy = export_model.evaluate(raw_test_ds)
print("Accuracy: {:2.2%}".format(binary_accuracy))

250/250 [==============================] - 1s 4ms/step - loss: 0.5180 - accuracy: 0.8164
Accuracy: 81.64%

def get_string_labels(predicted_scores_batch):
  predicted_int_labels = tf.math.argmax(predicted_scores_batch, axis=1)
  predicted_labels = tf.gather(raw_train_ds.class_names, predicted_int_labels)
  return predicted_labels

inputs = [
    "how do I extract keys from a dict into a list?",  # 'python'
    "debug public static void main(string[] args) {...}",  # 'java'
]
predicted_scores = export_model.predict(inputs)
predicted_labels = get_string_labels(predicted_scores)
for input, label in zip(inputs, predicted_labels):
  print("Question: ", input)
  print("Predicted label: ", label.numpy())

Question:  how do I extract keys from a dict into a list?
Predicted label:  b'python'
Question:  debug public static void main(string[] args) {...}
Predicted label:  b'java'

DIRECTORY_URL = 'https://storage.googleapis.com/download.tensorflow.org/data/illiad/'
FILE_NAMES = ['cowper.txt', 'derby.txt', 'butler.txt']

for name in FILE_NAMES:
  text_dir = utils.get_file(name, origin=DIRECTORY_URL + name)

parent_dir = pathlib.Path(text_dir).parent
list(parent_dir.iterdir())

Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/cowper.txt
819200/815980 [==============================] - 0s 0us/step
827392/815980 [==============================] - 0s 0us/step
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/derby.txt
811008/809730 [==============================] - 0s 0us/step
819200/809730 [==============================] - 0s 0us/step
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/butler.txt
811008/807992 [==============================] - 0s 0us/step
819200/807992 [==============================] - 0s 0us/step
[PosixPath('/home/kbuilder/.keras/datasets/mnist.npz'),
 PosixPath('/home/kbuilder/.keras/datasets/heart.csv'),
 PosixPath('/home/kbuilder/.keras/datasets/fashion-mnist'),
 PosixPath('/home/kbuilder/.keras/datasets/derby.txt'),
 PosixPath('/home/kbuilder/.keras/datasets/HIGGS.csv.gz'),
 PosixPath('/home/kbuilder/.keras/datasets/butler.txt'),
 PosixPath('/home/kbuilder/.keras/datasets/cowper.txt')]

def labeler(example, index):
  return example, tf.cast(index, tf.int64)

labeled_data_sets = []

for i, file_name in enumerate(FILE_NAMES):
  lines_dataset = tf.data.TextLineDataset(str(parent_dir/file_name))
  labeled_dataset = lines_dataset.map(lambda ex: labeler(ex, i))
  labeled_data_sets.append(labeled_dataset)

BUFFER_SIZE = 50000
BATCH_SIZE = 64
VALIDATION_SIZE = 5000

all_labeled_data = labeled_data_sets[0]
for labeled_dataset in labeled_data_sets[1:]:
  all_labeled_data = all_labeled_data.concatenate(labeled_dataset)

all_labeled_data = all_labeled_data.shuffle(
    BUFFER_SIZE, reshuffle_each_iteration=False)

for text, label in all_labeled_data.take(10):
  print("Sentence: ", text.numpy())
  print("Label:", label.numpy())

Sentence:  b"They slew, and shar'd, by tents, the ev'ning meal."
Label: 1
Sentence:  b'Achaeans, have them. At daybreak we will arm and fight about the ships;'
Label: 2
Sentence:  b'To whom, the foam-sprung Goddess, thus incensed.'
Label: 0
Sentence:  b'A respite (if the Atrid\xc3\xa6 so incline)'
Label: 0
Sentence:  b'therefore, let us all do as I say; we have eaten and drunk our fill,'
Label: 2
Sentence:  b'While morning lasted, and the light of day'
Label: 0
Sentence:  b'And, lifeless, instant, on the field he fell.'
Label: 0
Sentence:  b"Which bear renown'd Achilles o'er the field."
Label: 0
Sentence:  b'However short, to breathe again, so close'
Label: 0
Sentence:  b'through all their ranks, broke the battalions of the enemy. Agamemnon'
Label: 2

tokenizer = tf_text.UnicodeScriptTokenizer()

def tokenize(text, unused_label):
  lower_case = tf_text.case_fold_utf8(text)
  return tokenizer.tokenize(lower_case)

tokenized_ds = all_labeled_data.map(tokenize)

for text_batch in tokenized_ds.take(5):
  print("Tokens: ", text_batch.numpy())

Tokens:  [b'they' b'slew' b',' b'and' b'shar' b"'" b'd' b',' b'by' b'tents' b','
 b'the' b'ev' b"'" b'ning' b'meal' b'.']
Tokens:  [b'achaeans' b',' b'have' b'them' b'.' b'at' b'daybreak' b'we' b'will'
 b'arm' b'and' b'fight' b'about' b'the' b'ships' b';']
Tokens:  [b'to' b'whom' b',' b'the' b'foam' b'-' b'sprung' b'goddess' b',' b'thus'
 b'incensed' b'.']
Tokens:  [b'a' b'respite' b'(' b'if' b'the' b'atrid\xc3\xa6' b'so' b'incline' b')']
Tokens:  [b'therefore' b',' b'let' b'us' b'all' b'do' b'as' b'i' b'say' b';' b'we'
 b'have' b'eaten' b'and' b'drunk' b'our' b'fill' b',']

tokenized_ds = configure_dataset(tokenized_ds)

vocab_dict = collections.defaultdict(lambda: 0)
for toks in tokenized_ds.as_numpy_iterator():
  for tok in toks:
    vocab_dict[tok] += 1

vocab = sorted(vocab_dict.items(), key=lambda x: x[1], reverse=True)
vocab = [token for token, count in vocab]
vocab = vocab[:VOCAB_SIZE]
vocab_size = len(vocab)
print("Vocab size: ", vocab_size)
print("First five vocab entries:", vocab[:5])

Vocab size:  10000
First five vocab entries: [b',', b'the', b'and', b"'", b'of']

keys = vocab
values = range(2, len(vocab) + 2)  # Reserve `0` for padding, `1` for OOV tokens.

init = tf.lookup.KeyValueTensorInitializer(
    keys, values, key_dtype=tf.string, value_dtype=tf.int64)

num_oov_buckets = 1
vocab_table = tf.lookup.StaticVocabularyTable(init, num_oov_buckets)

def preprocess_text(text, label):
  standardized = tf_text.case_fold_utf8(text)
  tokenized = tokenizer.tokenize(standardized)
  vectorized = vocab_table.lookup(tokenized)
  return vectorized, label

example_text, example_label = next(iter(all_labeled_data))
print("Sentence: ", example_text.numpy())
vectorized_text, example_label = preprocess_text(example_text, example_label)
print("Vectorized sentence: ", vectorized_text.numpy())

Sentence:  b"They slew, and shar'd, by tents, the ev'ning meal."
Vectorized sentence:  [  27  307    2    4 2902    5    9    2   26  617    2    3  543    5
  885 1007    7]

all_encoded_data = all_labeled_data.map(preprocess_text)

train_data = all_encoded_data.skip(VALIDATION_SIZE).shuffle(BUFFER_SIZE)
validation_data = all_encoded_data.take(VALIDATION_SIZE)

train_data = train_data.padded_batch(BATCH_SIZE)
validation_data = validation_data.padded_batch(BATCH_SIZE)

sample_text, sample_labels = next(iter(validation_data))
print("Text batch shape: ", sample_text.shape)
print("Label batch shape: ", sample_labels.shape)
print("First text example: ", sample_text[0])
print("First label example: ", sample_labels[0])

Text batch shape:  (64, 18)
Label batch shape:  (64,)
First text example:  tf.Tensor(
[  27  307    2    4 2902    5    9    2   26  617    2    3  543    5
  885 1007    7    0], shape=(18,), dtype=int64)
First label example:  tf.Tensor(1, shape=(), dtype=int64)

vocab_size += 2

train_data = configure_dataset(train_data)
validation_data = configure_dataset(validation_data)

model = create_model(vocab_size=vocab_size, num_labels=3)

model.compile(
    optimizer='adam',
    loss=losses.SparseCategoricalCrossentropy(from_logits=True),
    metrics=['accuracy'])

history = model.fit(train_data, validation_data=validation_data, epochs=3)

Epoch 1/3
697/697 [==============================] - 28s 9ms/step - loss: 0.5224 - accuracy: 0.7657 - val_loss: 0.3604 - val_accuracy: 0.8448
Epoch 2/3
697/697 [==============================] - 3s 4ms/step - loss: 0.2856 - accuracy: 0.8826 - val_loss: 0.3490 - val_accuracy: 0.8540
Epoch 3/3
697/697 [==============================] - 3s 4ms/step - loss: 0.1931 - accuracy: 0.9262 - val_loss: 0.3780 - val_accuracy: 0.8496

loss, accuracy = model.evaluate(validation_data)

print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))

79/79 [==============================] - 1s 2ms/step - loss: 0.3780 - accuracy: 0.8496
Loss:  0.3780021369457245
Accuracy: 84.96%

preprocess_layer = TextVectorization(
    max_tokens=vocab_size,
    standardize=tf_text.case_fold_utf8,
    split=tokenizer.tokenize,
    output_mode='int',
    output_sequence_length=MAX_SEQUENCE_LENGTH)

preprocess_layer.set_vocabulary(vocab)

/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/numpy/core/numeric.py:2468: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison
  return bool(asarray(a1 == a2).all())
/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/keras/layers/preprocessing/index_lookup.py:458: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison
  if self.mask_token is not None and self.mask_token in tokens:

export_model = tf.keras.Sequential(
    [preprocess_layer, model,
     layers.Activation('sigmoid')])

export_model.compile(
    loss=losses.SparseCategoricalCrossentropy(from_logits=False),
    optimizer='adam',
    metrics=['accuracy'])

# Create a test dataset of raw strings.
test_ds = all_labeled_data.take(VALIDATION_SIZE).batch(BATCH_SIZE)
test_ds = configure_dataset(test_ds)

loss, accuracy = export_model.evaluate(test_ds)

print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))

2022-12-14 20:58:05.420812: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:907] Skipping loop optimization for Merge node with control input: sequential_4/text_vectorization_2/UnicodeScriptTokenize/Assert_1/AssertGuard/branch_executed/_185
79/79 [==============================] - 6s 8ms/step - loss: 0.5388 - accuracy: 0.7914
Loss:  0.5388292670249939
Accuracy: 79.14%

inputs = [
    "Join'd to th' Ionians with their flowing robes,",  # Label: 1
    "the allies, and his armour flashed about him so that he seemed to all",  # Label: 2
    "And with loud clangor of his arms he fell.",  # Label: 0
]

predicted_scores = export_model.predict(inputs)
predicted_labels = tf.math.argmax(predicted_scores, axis=1)

for input, label in zip(inputs, predicted_labels):
  print("Question: ", input)
  print("Predicted label: ", label.numpy())

2022-12-14 20:58:08.859336: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:907] Skipping loop optimization for Merge node with control input: sequential_4/text_vectorization_2/UnicodeScriptTokenize/Assert_1/AssertGuard/branch_executed/_185
Question:  Join'd to th' Ionians with their flowing robes,
Predicted label:  1
Question:  the allies, and his armour flashed about him so that he seemed to all
Predicted label:  2
Question:  And with loud clangor of his arms he fell.
Predicted label:  0

# Training set.
train_ds = tfds.load(
    'imdb_reviews',
    split='train[:80%]',
    batch_size=BATCH_SIZE,
    shuffle_files=True,
    as_supervised=True)

# Validation set.
val_ds = tfds.load(
    'imdb_reviews',
    split='train[80%:]',
    batch_size=BATCH_SIZE,
    shuffle_files=True,
    as_supervised=True)

for review_batch, label_batch in val_ds.take(1):
  for i in range(5):
    print("Review: ", review_batch[i].numpy())
    print("Label: ", label_batch[i].numpy())

Review:  b"Instead, go to the zoo, buy some peanuts and feed 'em to the monkeys. Monkeys are funny. People with amnesia who don't say much, just sit there with vacant eyes are not all that funny.<br /><br />Black comedy? There isn't a black person in it, and there isn't one funny thing in it either.<br /><br />Walmart buys these things up somehow and puts them on their dollar rack. It's labeled Unrated. I think they took out the topless scene. They may have taken out other stuff too, who knows? All we know is that whatever they took out, isn't there any more.<br /><br />The acting seemed OK to me. There's a lot of unfathomables tho. It's supposed to be a city? It's supposed to be a big lake? If it's so hot in the church people are fanning themselves, why are they all wearing coats?"
Label:  0
Review:  b'Well, was Morgan Freeman any more unusual as God than George Burns? This film sure was better than that bore, "Oh, God". I was totally engrossed and LMAO all the way through. Carrey was perfect as the out of sorts anchorman wannabe, and Aniston carried off her part as the frustrated girlfriend in her usual well played performance. I, for one, don\'t consider her to be either ugly or untalented. I think my favorite scene was when Carrey opened up the file cabinet thinking it could never hold his life history. See if you can spot the file in the cabinet that holds the events of his bathroom humor: I was rolling over this one. Well written and even better played out, this comedy will go down as one of this funnyman\'s best.'
Label:  1
Review:  b'I remember stumbling upon this special while channel-surfing in 1965. I had never heard of Barbra before. When the show was over, I thought "This is probably the best thing on TV I will ever see in my life." 42 years later, that has held true. There is still nothing so amazing, so honestly astonishing as the talent that was displayed here. You can talk about all the super-stars you want to, this is the most superlative of them all!<br /><br />You name it, she can do it. Comedy, pathos, sultry seduction, ballads, Barbra is truly a story-teller. Her ability to pull off anything she attempts is legendary. But this special was made in the beginning, and helped to create the legend that she quickly became. In spite of rising so far in such a short time, she has fulfilled the promise, revealing more of her talents as she went along. But they are all here from the very beginning. You will not be disappointed in viewing this.'
Label:  1
Review:  b"Firstly, I would like to point out that people who have criticised this film have made some glaring errors. Anything that has a rating below 6/10 is clearly utter nonsense.<br /><br />Creep is an absolutely fantastic film with amazing film effects. The actors are highly believable, the narrative thought provoking and the horror and graphical content extremely disturbing. <br /><br />There is much mystique in this film. Many questions arise as the audience are revealed to the strange and freakish creature that makes habitat in the dark rat ridden tunnels. How was 'Craig' created and what happened to him?<br /><br />A fantastic film with a large chill factor. A film with so many unanswered questions and a film that needs to be appreciated along with others like 28 Days Later, The Bunker, Dog Soldiers and Deathwatch.<br /><br />Look forward to more of these fantastic films!!"
Label:  1
Review:  b"I'm sorry but I didn't like this doc very much. I can think of a million ways it could have been better. The people who made it obviously don't have much imagination. The interviews aren't very interesting and no real insight is offered. The footage isn't assembled in a very informative way, either. It's too bad because this is a movie that really deserves spellbinding special features. One thing I'll say is that Isabella Rosselini gets more beautiful the older she gets. All considered, this only gets a '4.'"
Label:  0

vectorize_layer = TextVectorization(
    max_tokens=VOCAB_SIZE,
    output_mode='int',
    output_sequence_length=MAX_SEQUENCE_LENGTH)

# Make a text-only dataset (without labels), then call `TextVectorization.adapt`.
train_text = train_ds.map(lambda text, labels: text)
vectorize_layer.adapt(train_text)

def vectorize_text(text, label):
  text = tf.expand_dims(text, -1)
  return vectorize_layer(text), label

train_ds = train_ds.map(vectorize_text)
val_ds = val_ds.map(vectorize_text)

# Configure datasets for performance as before.
train_ds = configure_dataset(train_ds)
val_ds = configure_dataset(val_ds)

model = create_model(vocab_size=VOCAB_SIZE + 1, num_labels=1)
model.summary()

Model: "sequential_5"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 embedding_2 (Embedding)     (None, None, 64)          640064    
                                                                 
 conv1d_2 (Conv1D)           (None, None, 64)          20544     
                                                                 
 global_max_pooling1d_2 (Glo  (None, 64)               0         
 balMaxPooling1D)                                                
                                                                 
 dense_3 (Dense)             (None, 1)                 65        
                                                                 
=================================================================
Total params: 660,673
Trainable params: 660,673
Non-trainable params: 0
_________________________________________________________________

model.compile(
    loss=losses.BinaryCrossentropy(from_logits=True),
    optimizer='adam',
    metrics=['accuracy'])

history = model.fit(train_ds, validation_data=val_ds, epochs=3)

Epoch 1/3
313/313 [==============================] - 3s 6ms/step - loss: 0.5353 - accuracy: 0.6667 - val_loss: 0.3715 - val_accuracy: 0.8270
Epoch 2/3
313/313 [==============================] - 1s 4ms/step - loss: 0.2973 - accuracy: 0.8699 - val_loss: 0.3170 - val_accuracy: 0.8552
Epoch 3/3
313/313 [==============================] - 1s 4ms/step - loss: 0.1812 - accuracy: 0.9301 - val_loss: 0.3233 - val_accuracy: 0.8606

loss, accuracy = model.evaluate(val_ds)

print("Loss: ", loss)
print("Accuracy: {:2.2%}".format(accuracy))

79/79 [==============================] - 0s 2ms/step - loss: 0.3233 - accuracy: 0.8606
Loss:  0.32325324416160583
Accuracy: 86.06%

export_model = tf.keras.Sequential(
    [vectorize_layer, model,
     layers.Activation('sigmoid')])

export_model.compile(
    loss=losses.SparseCategoricalCrossentropy(from_logits=False),
    optimizer='adam',
    metrics=['accuracy'])

# 0 --> negative review
# 1 --> positive review
inputs = [
    "This is a fantastic movie.",
    "This is a bad movie.",
    "This movie was so bad that it was good.",
    "I will never say yes to watching this movie.",
]

predicted_scores = export_model.predict(inputs)
predicted_labels = [int(round(x[0])) for x in predicted_scores]

for input, label in zip(inputs, predicted_labels):
  print("Question: ", input)
  print("Predicted label: ", label)

Question:  This is a fantastic movie.
Predicted label:  1
Question:  This is a bad movie.
Predicted label:  0
Question:  This movie was so bad that it was good.
Predicted label:  1
Question:  I will never say yes to watching this movie.
Predicted label:  1