my code is
import streamlit as st
import pickle
import string
from nltk.corpus import stopwords
import nltk
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
def transform_text(text):
text = text.lower()
text = nltk.word_tokenize(text)
y = []
for i in text:
if i.isalnum():
y.append(i)
text = y[:]
y.clear()
for i in text:
if i not in stopwords.words('english') and i not in string.punctuation:
y.append(i)
text = y[:]
y.clear()
for i in text:
y.append(ps.stem(i))
return " ".join(y)
tfidf = pickle.load(open('vectorizer.pkl','rb'))
model = pickle.load(open('model.pkl','rb'))
st.title("Email/SMS Spam Classifier")
input_sms = st.text_area("Enter the message")
if st.button('Predict'):
# 1. preprocess
transformed_sms = transform_text(input_sms)
# 2. vectorize
vector_input = tfidf.transform([transformed_sms])
# 3. predict
result = model.predict(vector_input)[0]
# 4. Display
if result == 1:
st.header("Spam")
else:
st.header("Not Spam")
Related
I was trying to deploy ml model using node_js with help of ChildProcess package ,while running __predict(), it is taking too long and end with code_1 error.
Here I share all related code to decode the issue :
Model python code -->
import keras
import time
start = time.time()
encoder = keras.models.load_model('enc', compile = False)
decoder = keras.models.load_model('dec', compile = False)
import numpy as np
from flask import Flask, request, jsonify , render_template
import tensorflow as tf
import pickle
import string
import re
from keras_preprocessing.sequence import pad_sequences
def initialize_hidden_state():
return tf.zeros((1, 1024))
eng_tokenizer , hin_tokenizer = pickle.load( open('tokenizer.pkl','rb'))
def clean(text):
text = text.lower()
special_char = set(string.punctuation+'ред') # Set of all special characters
# Remove all the special characters
text = ''.join(word for word in text if word not in special_char)
seq = eng_tokenizer.texts_to_sequences([text])
seq = pad_sequences(seq, maxlen=23, padding='post')
return seq
def __predict(data):
# Get the data from the POST request.
#data = request.get_json(force=True)
clean_input = clean(data)
# Make prediction using model loaded from disk as per the data.
hidden_enc = initialize_hidden_state()
enc_out, enc_hidden = encoder(clean_input, hidden_enc)
result = ''
dec_hidden = enc_hidden
dec_input = tf.expand_dims(hin_tokenizer.texts_to_sequences(['<Start>'])[0], 0)
#------------------------------------------------------------------
for t in range(25):
predictions, dec_hidden, attention_weights = decoder(dec_input, dec_hidden, enc_out)
predicted_id = tf.argmax(predictions[0]).numpy()
x = hin_tokenizer.sequences_to_texts([[predicted_id]])[0]
if x == 'end':
break
result += x + ' '
# the predicted ID is fed back into the model
dec_input = tf.expand_dims([predicted_id], 0)
CLEANR = re.compile(r"([A-Za-z])", re.DOTALL)
result = re.sub(CLEANR, '', result)
return result
# import json
# with open('data.json', 'r') as openfile:
# json_object = json.load(openfile).get('data')
data =__predict("file")
end= time.time()
# print(start-end)
data1 = data +"abcd"
print(data1)
# print("abcd")
# dictionary = {
# "data": data,
# }
# json_object = json.dumps(dictionary, indent=2)
# with open("result.json", "w") as outfile:
# outfile.write(json_object)
When I type print("abcd") or print(start-end), it is giving result ,ending with code_0. But when I type print("data") not giving any result and ending with code_1 .
Here is the childProcess code -->
app.get('/', (req, res) => {
let dataToSend
let largeDataSet = []
// spawn new child process to call the python script
const python = spawn('python', ['app.py'])
// console.log(python);
// collect data from script
python.stdout.on('data', function (data) {
console.log('Pipe data from python script ...')
//dataToSend = data;
largeDataSet.push(data)
})
// in close event we are sure that stream is from child process is closed
python.on('close', (code) => {
console.log(`child process close all stdio with code ${code}`)
// send data to browser
// largeDataSet = []
console.log(largeDataSet.join(''));
res.send(largeDataSet.join(''))
})
})
Here is the error --->
child process close all stdio with code 1
Pls help , I tried to understand the problem but failed severely even in understanding it.
Thanks in advance !!!
I would like to compare log and pct change f the two symbols, but the following error appears:
KeyError: 'Adj Close'
import datetime
import pandas as pd
import numpy as np
import yfinance as yf
start = datetime.datetime(2017, 10, 1)
end = datetime.datetime.now()
symbols = ['BTC-USD', 'ETH-USD']
df = pd.DataFrame()
for i in symbols:
data = yf.download(i, start=None, end=None,show_errors=("True"),
period="4y", interval="1mo")
df[i] = data['Adj Close'].pct_change().dropna()
df['log_stuff'] = \
np.log(df['Adj Close'].astype('float64')/df['Adj Close'].astype('float64').shift(1))
df[['pct_change', 'log_stuff','df']].plot();
You could try the following. Please note, that you can also pass a list to download(), so no loops are required.
import numpy as np
import pandas as pd
import yfinance as yf
symbols = ['BTC-USD', 'ETH-USD']
data = yf.download(symbols, period="4y", interval="1mo")
# calculate pct return
pct_data = data['Adj Close'].pct_change()
pct_data = pct_data.add_suffix('_pct')
# calculate log returns
log_data = np.log(data['Adj Close']) - np.log(data['Adj Close'].shift(1))
log_data = log_data.add_suffix('_log')
# combine returns and drop na values
combined_data = pd.concat([pct_data,log_data], axis=1).dropna()
print(combined_data)
This will yield the following output:
BTC-USD_pct ETH-USD_pct BTC-USD_log ETH-USD_log
Date
2017-12-01 0.383326 0.692483 0.324490 0.526197
2018-01-01 -0.277987 0.477813 -0.325713 0.390564
2018-02-01 0.017298 -0.235276 0.017150 -0.268240
...
Code for a single raster file:
import geopandas as gpd
#import os
import rasterio
import scipy.sparse as sparse
import pandas as pd
import numpy as np
# Create an empty pandas dataframe called 'table'
table = pd.DataFrame(index = np.arange(0,1))
# Read the points shapefile using GeoPandas
stations = gpd.read_file(r'E:/anakonda/Shape files/AAQ_st1/AAQ_ST1.shp')
stations['lon'] = stations['geometry'].x
stations['lat'] = stations['geometry'].y
Matrix = pd.DataFrame()
# Iterate through the rasters and save the data as individual arrays to a Matrix
dataset = rasterio.open(r'E:/anakonda/LST_day/MOD11A1.006_LST_Day_1km_doy2019082_aid0001.tif')
data_array = dataset.read(1)
data_array_sparse = sparse.coo_matrix(data_array, shape = (351, 545))
for records_date in Matrix.columns.tolist():
a = Matrix
LST_day_value = a.loc[int(row)][int(col)]
table[records_date] = LST_day_value
transpose_mat = table.T
transpose_mat.rename(columns = {0: 'LST_Day(Kel)'}, inplace = True)
transpose_mat.to_csv(r'E:/anakonda/LST_day'+'\\'+station_name+'.csv')
Error code lines:
LST_day_value = a.loc[int(row)][int(col)]
transpose_mat.to_csv(r'E:/anakonda/LST_day'+'\'+station_name+'.csv')
Errors Shown:
Undefined Name 'row' (pyflakes E)
Undefined Name 'col' (pyflakes E)
NameError: name 'transpose_mat' is not defined
I'm using the above code for creating a Raster Time-series for Modis LST data. the code ran well till 'transposing the matrix'. the error shown is mentioned below the code. Im new to python, so kindly help me with this issue.
import os
import rasterio
import scipy.sparse as sparse
import pandas as pd
import numpy as np
# Create an empty pandas dataframe called 'table'
table = pd.DataFrame(index = np.arange(0,1))
# Read the points shapefile using GeoPandas
stations = gpd.read_file(r'E:/anakonda/Shape files/AAQ_st1/AAQ_ST1.shp')
stations['lon'] = stations['geometry'].x
stations['lat'] = stations['geometry'].y
Matrix = pd.DataFrame()
# Iterate through the rasters and save the data as individual arrays to a Matrix
for files in os.listdir(r'E:/anakonda/LST_Night'):
if files[-4: ] == '.tif':
dataset = rasterio.open(r'E:/anakonda/LST_Night'+'\\'+files)
data_array = dataset.read(1)
data_array_sparse = sparse.coo_matrix(data_array, shape = (351,545))
data = files[ :-20]
Matrix[data] = data_array_sparse.toarray().tolist()
print('Processing is done for the raster: '+ files[:-20])
# Iterate through the stations and get the corresponding row and column for the related x, y coordinates
for index, row in stations.iterrows():
station_name = str(row['Station'])
lon = float(row['lon'])
lat = float(row['lat'])
x,y = (lon, lat)
row, col = dataset.index(x, y)
print('Processing: '+ station_name)
# Pick the LST value from each stored raster array and record it into the previously created 'table'
for records_date in Matrix.columns.tolist():
a = Matrix[records_date]
LST_Night_value = a.loc[int(row)][int(col)]
table[records_date] = LST_Night_value
transpose_mat = table.T
transpose_mat.rename(columns = {0: 'LstNight(Kel)'}, inplace = True)
transpose_mat.to_csv(r'E:/anakonda/LST_Night'+'\\'+station_name+'.csv')```
This is the error shown:
```File "C:\Anaconda\envs\timeseries\lib\site-packages\pandas\core\indexes\range.py", line 357, in get_loc
raise KeyError(key) from err
KeyError: 2278```
I am using Q learning and the program should be able to play the game after some tries but it is not learning even when the epsilon value if 0.1.
I have tried changing the batch size the memory size. I have changed the code to give -1 reward if the player dies.
import gym
import numpy as np
import random
import tensorflow as tf
import numpy as np
from time import time
import keyboard
import sys
import time
env = gym.make("Breakout-ram-v4")
observationSpace = env.observation_space
actionSpace= env.action_space
episode = 500
class Model_QNN :
def __init__(self):
self.memory = []
self.MAX_MEMORY_TO_USE = 60_000
self.gamma = 0.9
self.model = tf.keras.Sequential([
tf.keras.layers.Flatten(input_shape=(128,1)),
tf.keras.layers.Dense(256,activation="relu"),
tf.keras.layers.Dense(64,activation="relu"),
tf.keras.layers.Dense(actionSpace.n , activation= "softmax")
])
self.model.compile(optimizer="adam",loss="mse",metrics=["accuracy"])
def remember(self, steps , done):
self.memory.append([steps,done])
if(len(self.memory) >= self.MAX_MEMORY_TO_USE):
del self.memory[0]
def replay(self,batch_size= 32):
states, targets_f = [], []
if(len(self.memory)< batch_size) :
return
else:
mini = random.sample(self.memory,batch_size)
states ,targets = [], []
for steps , done in mini :
target= steps[2] ;
if not done :
target = steps[2] + (self.gamma* np.amax(self.model.predict(steps[3].reshape(1,128,1))[0]))
target_f = self.model.predict(steps[0].reshape(1,128,1))
target_f[0][steps[1]] = target
states.append(steps[0])
targets.append(target_f[0])
self.model.fit(np.array(states).reshape(len(states),128,1), np.array(targets),verbose=0,epochs=10)
def act(self,state,ep):
if(random.random()< ep):
action = actionSpace.sample()
else :
np.array([state]).shape
action= self.model.predict(state.reshape(1,128,1))
action = np.argmax(action)
return action;
def saveModel (self):
print("Saving")
self.model.save("NEWNAMEDONE")
def saveBackup(self,num):
self.model.save("NEWNAME"+str(int(num)))
def main():
agent= Model_QNN();
epsilon=0.9
t_end = time.time()
score= 0
for e in range(2000):
print("Working on episode : "+str(e)+" eps "+str(epsilon)+" Score " + str(score))
preState = env.reset()
preState,reward,done,_ = env.step(1)
mainLife=5
done = False
score= 0
icount = 0
render=False
if e % 400 ==0 and not e==0:
render =True
while not done:
icount+=1
if render:
env.render()
if keyboard.is_pressed('q'):
agent.saveBackup(100)
agent.saveModel()
quit()
rewrd=0
if ( _["ale.lives"] < mainLife ):
mainLife-=1
rewrd=-1
action=1
else:
action = agent.act(preState,epsilon)
newState,reward,done,_ = env.step(action)
if rewrd ==-1 :
reward =-1
agent.remember([preState/255,action,reward,newState/255],done);
preState= newState;
score+=reward
if done :
break
agent.replay(1024)
if epsilon >= 0.18 :
epsilon = epsilon * 0.995;
if ((e+1)%500==0):
agent.saveBackup((e+1)/20)
agent.saveModel()
if __name__=='__main__':
main()
There is no error message the program should learn and it is not
Why are you using Softmax on your output layer?
If you want to use Softmax use Cross-Entropy as your loss. However, it looks like you're trying to implement a value based learning system. The activation function on your output layer should be linear.
I suggest you try your implementation on Cartpole-v0 then LunarLanding-v2 first.
Those are solved environments and a great place to sanity check your code.
"There is no error message the program should learn and it is not."
Welcome to ML where things fail silently.
I am beginner of python language,natural language processing,deep learning,neural networks.I want to execute a program which convert text file into vector by using word2vec in python..someone please help me
import math
import nltk file = "/home/stephy/Demo/textfile.txt"
import numpy as np
def loadGloveModel(gloveFile):
with open(gloveFile, encoding="utf8" ) as f:
content = f.readlines()
model = {} for line in content:
splitLine = line.split()
word = splitLine[0]
embedding = np.array([float(val) for val in splitLine[1:]])
model[word] = embedding
print ("Done.",len(model)," words loaded!")
return model
model= loadGloveModel(file)
print (model['file'])