Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitb4988ee

Browse files
committed
add python code generator in machine-learning/nlp/text-generator
1 parentd8c41dd commitb4988ee

File tree

5 files changed

+78
-56
lines changed

5 files changed

+78
-56
lines changed
Lines changed: 28 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -1,32 +1,39 @@
11
#[How to Build a Text Generator using Keras in Python](https://www.thepythoncode.com/article/text-generation-keras-python)
22
To run this:
33
-`pip3 install -r requirements.txt`
4-
- To use pre-trained text generator model that was trained on Alice's wonderland text book:
4+
- To use pre-trained text generator model that was trained on Alice's wonderland text book or Python Code:
55
```
66
python generate.py --help
77
```
8-
**Output:**
8+
This will prompt you with the choice, seed and number of characters you want!
9+
Here is an example on Alice's wonderland with 200 characters:
910
```
10-
usage: generate.py [-h] [-n N_CHARS] seed
11-
12-
Text generator that was trained on Alice's Adventures in the Wonderland book.
13-
14-
positional arguments:
15-
seed Seed text to start with, can be any english text, but
16-
it's preferable you take from the book itself.
17-
18-
optional arguments:
19-
-h, --help show this help message and exit
20-
-n N_CHARS, --n-chars N_CHARS
21-
Number of characters to generate, default is 200.
22-
```
23-
Generating 200 characters with that seed:
24-
```
25-
python generate.py "down down down there was nothing else to do so alice soon began talking again " -n 200
11+
Generated text:
12+
the duchess asked to the dormouse she wanted about for the world all her life i dont know what to think that it was so much sort of mine for the world a little like a stalking and was going to the mou
2613
```
27-
**Output:**
14+
Another example:
2815
```
29-
Generating text: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 200/200 [00:40<00:00, 5.02it/s]
16+
Please choose which model you want to generate text with:
17+
1 - Alice's wonderland
18+
2 - Python Code
19+
2
20+
Enter the seed, enter q to quit, maximum 100 characters:
21+
import os
22+
import sys
23+
import subprocess
24+
import numpy as np
25+
q
26+
Enter number of characters you want to generate: 200
27+
Generating text: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 200/200 [00:44<00:00, 4.68it/s]
3028
Generated text:
31-
the duchess asked to the dormouse she wanted about for the world all her life i dont know what to think that it was so much sort of mine for the world a little like a stalking and was going to the mou
29+
import pandas as pd
30+
import os
31+
import numpy as np
32+
import pandas as pd
33+
import matplotlib.pyplot as plt
34+
import numpy as np
35+
import tensorflow as tf
36+
37+
config = tf.configproto(intra_op_parallelism_threads=n
38+
3239
```
Binary file not shown.
Binary file not shown.

‎machine-learning/nlp/text-generator/generate.py

Lines changed: 50 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -5,10 +5,22 @@
55
fromkeras.layersimportDense,LSTM,Dropout,Activation
66
fromkeras.callbacksimportModelCheckpoint
77

8-
# seed = "do not try to"
98

10-
char2int=pickle.load(open("data/wonderland-char2int.pickle","rb"))
11-
int2char=pickle.load(open("data/wonderland-int2char.pickle","rb"))
9+
10+
message="""
11+
Please choose which model you want to generate text with:
12+
1 - Alice's wonderland
13+
2 - Python Code
14+
"""
15+
choice=int(input(message))
16+
assertchoice==1orchoice==2
17+
18+
ifchoice==1:
19+
char2int=pickle.load(open("data/wonderland-char2int.pickle","rb"))
20+
int2char=pickle.load(open("data/wonderland-int2char.pickle","rb"))
21+
elifchoice==2:
22+
char2int=pickle.load(open("data/python-char2int.pickle","rb"))
23+
int2char=pickle.load(open("data/python-int2char.pickle","rb"))
1224

1325
sequence_length=100
1426
n_unique_chars=len(char2int)
@@ -21,35 +33,38 @@
2133
Dense(n_unique_chars,activation="softmax"),
2234
])
2335

24-
model.load_weights("results/wonderland-v2-0.75.h5")
25-
26-
if__name__=="__main__":
27-
importargparse
28-
parser=argparse.ArgumentParser(description="Text generator that was trained on Alice's Adventures in the Wonderland book.")
29-
parser.add_argument("seed",help="Seed text to start with, can be any english text, but it's preferable you take from the book itself.")
30-
parser.add_argument("-n","--n-chars",type=int,dest="n_chars",help="Number of characters to generate, default is 200.",default=200)
31-
args=parser.parse_args()
32-
33-
n_chars=args.n_chars
34-
seed=args.seed
35-
36-
# generate 400 characters
37-
generated=""
38-
foriintqdm.tqdm(range(n_chars),"Generating text"):
39-
# make the input sequence
40-
X=np.zeros((1,sequence_length,n_unique_chars))
41-
fort,charinenumerate(seed):
42-
X[0, (sequence_length-len(seed))+t,char2int[char]]=1
43-
# predict the next character
44-
predicted=model.predict(X,verbose=0)[0]
45-
# converting the vector to an integer
46-
next_index=np.argmax(predicted)
47-
# converting the integer to a character
48-
next_char=int2char[next_index]
49-
# add the character to results
50-
generated+=next_char
51-
# shift seed and the predicted character
52-
seed=seed[1:]+next_char
53-
54-
print("Generated text:")
55-
print(generated)
36+
ifchoice==1:
37+
model.load_weights("results/wonderland-v2-0.75.h5")
38+
elifchoice==2:
39+
model.load_weights("results/python-v2-0.30.h5")
40+
41+
seed=""
42+
print("Enter the seed, enter q to quit, maximum 100 characters:")
43+
whileTrue:
44+
result=input("")
45+
ifresult.lower()=="q":
46+
break
47+
seed+=f"{result}\n"
48+
seed=seed.lower()
49+
n_chars=int(input("Enter number of characters you want to generate: "))
50+
51+
# generate 400 characters
52+
generated=""
53+
foriintqdm.tqdm(range(n_chars),"Generating text"):
54+
# make the input sequence
55+
X=np.zeros((1,sequence_length,n_unique_chars))
56+
fort,charinenumerate(seed):
57+
X[0, (sequence_length-len(seed))+t,char2int[char]]=1
58+
# predict the next character
59+
predicted=model.predict(X,verbose=0)[0]
60+
# converting the vector to an integer
61+
next_index=np.argmax(predicted)
62+
# converting the integer to a character
63+
next_char=int2char[next_index]
64+
# add the character to results
65+
generated+=next_char
66+
# shift seed and the predicted character
67+
seed=seed[1:]+next_char
68+
69+
print("Generated text:")
70+
print(generated)
Binary file not shown.

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp