def getModelApi():
preprocessor = Preprocessing.Preprocessor()
summarizer = Summarizer.Summarizer('./vocab', './')
def preprocessorApi(article):
tokenized=preprocessor.tokenize(article)
tokenized=(' '.join(tokenized))
return preprocessor.adjust_article(tokenized.split('*N*')).encode('utf-8')
def modelApi(preprocessed_articles):
return summarizer.summarize(preprocessed_articles)
return preprocessorApi,modelApi
def index():
if request.method == 'POST':
try:
f = request.files['file1']
df = pd.read_excel(f)
df.columns = df.columns.str.replace(' ', '')
columns = [
'id', 'MRBTS', "redirFreqCdma",
"Item-redirGeranArfcnStructL-redirGeranArfcnPrio",
'redirGeranArfcnStructL', 'redirGeranBandIndicator',
'Item-redirGeranArfcnStructL-redirGeranArfcnValue'
]
preprocessor = Preprocessing.Preprocessor()
df = preprocessor.handle_missing_values(df)
df = preprocessor.remove_columns(df, columns)
filename1 = 'DTmodel_Pred_REDRTV1.sav'
loaded_model = pickle.load(open(filename1, 'rb'))
prediction = loaded_model.predict(df)
result = pd.DataFrame(prediction)
result.columns = ['Pred']
result = preprocessor.int_to_categorical(result)
final_sheet = pd.merge(df,
result,
left_index=True,
right_index=True)
print('final sheet is prepared')
resp = make_response(final_sheet.to_csv())
resp.headers[
"Content-Disposition"] = "attachment; filename=outputfile.csv"
resp.headers["Content-Type"] = "text/csv"
return resp
#final_sheet.to_excel('https://github.com/HardikDarshi/ML_Projects/tree/Master/outputfile.xlsx', index = True, header = True)
#final_sheet.save(os.path.join("uploads", final_sheet.filename))
#return 'Output file is saved to uploads folder'
except Exception as e:
print('The Exception message is:', e)
return 'Something is Wrong'
else:
return render_template('index.html')
# -*- coding:utf-8 -*-
from model import TextClassifier
import config
import Preprocessing
import pandas as pd
import numpy as np
if __name__ == '__main__':
p = Preprocessing.Preprocessor()
#读取训练集，验证集和测试集s
Train_raw_data = pd.read_csv(config.train_data_path)
Validation_raw_data = pd.read_csv(config.validate_data_path)
Test_raw_data = pd.read_csv(config.test_data_path)
tmp = p.preprocess_content(Train_raw_data['content'])
Train_sequences = p.preprocess_text(tmp, train_flag=True)
tmp = p.preprocess_content(Validation_raw_data['content'])
Validation_sequences = p.preprocess_text(tmp, train_flag=False)
tmp = p.preprocess_content(Test_raw_data['content'])
Test_sequences = p.preprocess_text(tmp, train_flag=False)
# # +Process Training Input, Validation Input, and Test Input
# # 1. Divide Content and word Tags
# # 2. Remove Stop Words
# # 3. Encoding word Tags
# # 4. Construct words Dictionary and Padding sequences
#
