def text_api_doc(request):
text = str(request.GET['text'])
usecase = str(request.GET['usecase'])
modelId = request.GET['modelId']
modelId = eval(modelId)
clientId = str(request.GET['clientId'])
params = str(request.GET['params'])
modelMap_df = pd.read_csv(projectDir+"/config/modelMapping.csv")
if modelId != None:
usecaseMap = ''.join(modelMap_df.ix[modelMap_df['modelId'] == modelId ,'usecase'].tolist())
modelName = modelMap_df.ix[modelMap_df['modelId'] == modelId ,'modelName'].tolist()
if text == '' :
results = {'Predicted Category':None,'Prediction Score':None}
return HttpResponse(json.dumps(results))
if usecase.lower() != usecaseMap.lower():
return HttpResponse("<h1 style='color: red'>Please provide the correct usecase for the modelId:%s<h1>" %modelId)
if usecase.lower() not in ['sentiment','survey']:
folderName = modelName
folderName = baseDir+"/"+''.join(folderName)+"/out"
try:
skl = SklCat()
transformedXTest = skl.run_text_vectorizeTransform([text], folderName = folderName, vectorizerFile = 'FeatureTransformer.p', pickler = None)
y_pred,y_prob_max = skl.run_text_execute_api_doc(transformedXTest, folderName = folderName, modelFile = 'Classifier.p', pickler=None, modelType = 'classification')
results = {'Predicted Category':list(y_pred),'Prediction Score':list(y_prob_max)}
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
elif usecase.lower() == 'sentiment':
sentimentPattern= modelName
sentimentPattern = ''.join(sentimentPattern)
try:
emo = Sentiment()
results = emo.run(text, modelType = sentimentPattern, args = [], kwargs = {})
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
elif usecase.lower() == 'survey':
ruleBaseFile = projectDir+"/config/ruleBase_v3.csv"
try:
sa = SurveyAnalysis()
results = sa.run(text,ruleBaseFile = ruleBaseFile)
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
else:
return HttpResponse("<h1 style='color: red'>Please provide the proper usecase..</h1>")
return HttpResponse(json.dumps(results))
else:
return HttpResponse("<h1>Please provide the modelId in URL</h1>")
def text_api(request):
text = str(request.GET['text'])
usecase = str(request.GET['usecase'])
modelId = request.GET['modelId']
modelId = eval(modelId)
clientId = str(request.GET['clientId'])
params = str(request.GET['params'])
modelMap_df = pd.read_csv(projectDir+"/config/modelMapping.csv")
results = []
records = eval(text)
if modelId != None:
usecaseMap = ''.join(modelMap_df.ix[modelMap_df['modelId'] == modelId ,'usecase'].tolist())
modelName = modelMap_df.ix[modelMap_df['modelId'] == modelId ,'modelName'].tolist()
if text == '' :
results = {'Predicted Category':None,'Prediction Score':None}
return HttpResponse(json.dumps(results))
if usecase.lower() != usecaseMap.lower():
return HttpResponse("<h1 style='color: red'>Please provide the correct usecase for the modelId:%s<h1>" %modelId)
if usecase.lower() not in ['sentiment','survey','ltv']:
df = pd.read_json(json.dumps(records)) # converting json string into dataframe
folderName = modelName
folderName = baseDir+"/"+''.join(folderName)+"/out"
try:
skl = SklCat()
#df = df.ix[df['lineBy']==2,:] #filtering customer lines
df['chat_intent'] = df['lineText'].apply(lambda x:skl.run_text_vectorizeTransform([str(x)], folderName = folderName, vectorizerFile = 'FeatureTransformer.p', pickler = None)).apply(lambda x: skl.run_text_execute_api_bulkDoc(x, folderName = folderName, modelFile = 'Classifier.p', pickler=None, modelType = 'classification'))
dfResults = df.ix[:,['sessionId','chat_intent']]
results = dfResults.to_json(orient='records')
'''
for doc in records:
text = doc['chat_text']
transformedXTest = skl.run_text_vectorizeTransform([text], folderName = folderName, vectorizerFile = 'FeatureTransformer.p', pickler = None)
y_pred,y_prob_max = skl.run_text_execute(transformedXTest, folderName = folderName, modelFile = 'Classifier.p', pickler=None, modelType = 'classification')
output = {'session_id':doc['session_id'],'chat_text':text ,'Predicted Category':list(y_pred),'Prediction Score':list(y_prob_max)}
results.append(output)
'''
return HttpResponse(json.dumps(results))
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
elif usecase.lower() == 'sentiment':
sentimentPattern= modelName
sentimentPattern = ''.join(sentimentPattern)
records = eval(text)
try:
emo = Sentiment()
results = []
jsonResults = {}
for doc in records:
jsonTemp = {}
jsonTemp['sessionId'] = doc['sessionId']
df_chat_data = pd.read_json(json.dumps(doc['chat_data']))
df_chat_data['sentiment'] = df_chat_data['lineText'].apply(lambda row: emo.run(row,modelType = sentimentPattern,args = [],kwargs={}))
df = df_chat_data.ix[:,['lineNum','sentiment']]
jsonObj = df.to_json(orient ='records')
each_line = json.loads(json.dumps(jsonObj))
jsonTemp['each_line'] = each_line
chat_sentiment = {}
chat_sentiment['overall'] = overallSentiment(df_chat_data['sentiment'])
lastlines = 2
chat_sentiment['last_line_sentiment'] = df_chat_data['lineText'].tail(lastlines).apply(lambda row: emo.run(row,modelType = sentimentPattern,args = [],kwargs={})).to_json(orient='records')
chat_sentiment['switches_to_postive'] = getPositivieSwitches(df_chat_data['sentiment'].tolist())
jsonTemp['chat_sentiment'] = chat_sentiment
results.append(jsonTemp)
'''
for doc in records:
text = doc['lineText']
output = emo.run(text, modelType = sentimentPattern, args = [], kwargs = {})
output['sessionId']= doc['sessionId']
output['lineText'] = text
results.append(output)
'''
return HttpResponse(json.dumps(results ,indent=5))
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
elif usecase.lower() == 'survey':
ruleBaseFile = projectDir+"/config/ruleBase_v3.csv"
try:
sa = SurveyAnalysis()
results = sa.run(text,ruleBaseFile = ruleBaseFile)
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
elif usecase.lower() == 'ltv':
folderName = modelName
folderName = baseDir+"/"+''.join(folderName)+"/out"
skl = SklCat()
results = []
jsonResults = {}
try:
for doc in records:
jsonTemp = {}
jsonTemp['sessionId'] = doc['sessionId']
df_chat_data = pd.read_json(json.dumps(doc['chat_data']))
if 'lineNum' not in df_chat_data.columns.tolist():
df_chat_data['lineNum'] = pd.Series(range(1, df_chat_data.shape[0]+1))
df_chat_data = df_chat_data.ix[df_chat_data['lineBy'] == 1,:] #filtering only agent lines
#ltv = df_chat_data['lineText'].apply(lambda x:skl.run_text_vectorizeTransform([str(x)], folderName = folderName, vectorizerFile = 'FeatureTransformer.p', pickler = None)).apply(lambda x: skl.run_text_execute_api_bulkDoc(x, folderName = folderName, modelFile = 'Classifier.p', pickler=None, modelType = 'classification',usecase='ltv'))
transformedXTest = skl.run_text_vectorizeTransform(df_chat_data['lineText'].tolist(), folderName = folderName, vectorizerFile = 'FeatureTransformer.p', pickler = None)
dfProb = skl.run_text_execute_api_bulkDoc(transformedXTest, folderName = folderName, modelFile = 'Classifier.p', pickler=None, modelType = 'classification',usecase='ltv')
#dfTest = df_chat_data.ix[df_chat_data['ltv'].apply(lambda x : len(x)!=0)]
if len(dfProb) != 0:
dfProb['lineNum'] = pd.Series(range(1, dfProb.shape[0]+1))
threshold = 0.2
dfMerged = pd.merge(df_chat_data, dfProb, how='left', left_on='lineNum', right_on='lineNum',suffixes = ('_x','_y'))
dfMerged = dfMerged.ix[:,['lineNum','y_pred','y_prob_max']]
dfMerged['flag'] = dfMerged.apply(lambda row: row['y_pred'] == 1 and row['y_prob_max'] > threshold,axis = 1)
ltv_agg = 1 if dfMerged['flag'].any() else 0
jsonTemp['chat_ltv'] = {'category':ltv_agg}
jsonObj = dfMerged.to_json(orient = 'records')
each_line = json.loads(json.dumps(jsonObj))
jsonTemp['each_line'] = each_line
results.append(jsonTemp)
return HttpResponse(json.dumps(results))
except Exception as e:
return HttpResponse("<h1 style='color: red'>Error Occured:%s</h1>" %e)
else:
return HttpResponse("<h1 style='color: red'>Please provide the proper usecase..</h1>")
#return HttpResponse(json.dumps(results))
else:
return HttpResponse("<h1>Please provide the modelId in URL</h1>")
def get_city_thresholds(self):
for city in self.senitiment_cities:
city_sentiment = Sentiment(city, self.to_tokenize, self.document_type)
city_sentiment.run()
