def post_logfile():
if request.method == 'GET':
log_file = request.args['symptom']
print(log_file)
diseaseclassifier = Trainer(tokenizer) #STARTS CLASIFIERS
with open("Dataset.csv", "r") as file: #OPENS DATASET
for i in file: #FOR EACH LINE
lines = file.next().split(",") #PARSE CSV <DISEASE> <SYMPTOM>
diseaseclassifier.train(lines[1], lines[0]) #TRAINING
diseaseclassifier = Classifier(diseaseclassifier.data, tokenizer)
classification = diseaseclassifier.classify(log_file) #CLASIFY INPUT
print classification
return json.dumps(dict(classification))
def post_logfile():
if request.method == 'POST':
log_file = request.args['symptom']
print(log_file)
diseaseclassifier = Trainer(tokenizer) #STARTS CLASIFIERS
with open("Dataset.csv", "r") as file: #OPENS DATASET
for i in file: #FOR EACH LINE
lines = file.next().split(",") #PARSE CSV <DISEASE> <SYMPTOM>
diseaseclassifier.train(lines[1], lines[0]) #TRAINING
diseaseclassifier = Classifier(diseaseclassifier.data, tokenizer)
classification = diseaseclassifier.classify(log_file) #CLASIFY INPUT
print classification
result = []
for item in classification:
obj = CustomType(item[0], item[1])
result.append(json.loads(obj.toJSON()))
# return json.dumps(OrderedDict(classification))
return json.dumps(result, indent=4)
import json, os, sys, re
from naiveBayesClassifier import tokenizer
from naiveBayesClassifier.trainer import Trainer
from naiveBayesClassifier.classifier import Classifier
##IMPORTS
'''
Usage:
python GuessDisease.py "symptomA symptomB symptomC"
Example INPUT:
python GuessDisease.py "agitation exhaustion vomit"
Example OUTPUT:
{
"disease": "influenza"
}
'''
##SETTING UP
diseaseclassifier = Trainer(tokenizer) #STARTS CLASIFIERS
with open("Dataset.csv", "r") as file: #OPENS DATASET
for i in file: #FOR EACH LINE
lines = file.next().split(",") #PARSE CSV <DISEASE> <SYMPTOM>
diseaseclassifier.train(lines[1], lines[0]) #TRAINING
diseaseclassifier = Classifier(diseaseclassifier.data, tokenizer)
classification = diseaseclassifier.classify(sys.argv[1]) #CLASIFY INPUT
print classification[0] #PRINT CLASIFICATION
['Cabbage Loopers', 'holes on leaves'],
[
'Cutworms',
'fat caterpillars, basically gray, brown, or black with 41 to 51 mm long when fully grown'
], ['Cutworms', 'damaged stem'],
[
'Bacterial Leaf Spot',
'small water-soaked spots on older leaves then quickly turn black'
], ['Bacterial Leaf Spot', 'holes on leaves'],
['Lettuce Drop', 'older leaves wilt'],
['Lettuce Drop', 'older leaves collapse'],
['Lettuce Drop',
'brown crown tissue'], ['Lettuce Drop', 'holes on leaves'],
['Anthracnose', 'water-soaked spots that turn yellow'],
[
'Anthracnose',
'white to pink spore masses of the fungus in the center of the lesions'
], ['Anthracnose', 'damaged leaf becomes papery'],
['Anthracnose', 'holes on leaves'], ['Tipburn', 'browing of leaf margins'],
['Tipburn', 'brown veins']
]
disease_classifier = Trainer(tokenizer)
for data in dataset:
disease_classifier.train(data[1], data[0])
disease_classifier = Classifier(disease_classifier.data, tokenizer)
classifications = disease_classifier.classify(sys.argv[1])
classifications_list = []
for classification in classifications:
classifications_list.append(classification[0])
print json.dumps({'classifications': classifications_list})
import json, os, sys, re
from naiveBayesClassifier import tokenizer
from naiveBayesClassifier.trainer import Trainer
from naiveBayesClassifier.classifier import Classifier
diseaseclassifier = Trainer(tokenizer)
with open("Dataset.csv", "r") as file:
for i in file: #FOR EACH LINE
lines = file.readline().split(",")
diseaseclassifier.train(lines[1], lines[0])
diseaseclassifier = Classifier(diseaseclassifier.data, tokenizer)
txt = input("enter symptomA symptomB symptomC")
classification = diseaseclassifier.classify(txt)
print(classification[0])
print(user_input)
if user_input:
return user_input
else:
if unique_symptoms[1]:
print("If you have any of these symptoms, enter as comma separated values")
for i in unique_symptoms[1]:
print(i)
user_input = input()
if user_input != '\n':
return user_input
return None
while True:
classification = diseaseclassifier.classify(','.join(initial_submitted_symptoms))
formatted_print(initial_submitted_symptoms, classification[:5])
other_possible_symptoms = []
for disease in classification[:5]:
d = disease[0]
other_possible_symptoms.append(
[symptom for symptom in disease_symptom_dict[d] if symptom not in initial_submitted_symptoms])
unique_symptoms = get_unique_symptoms()
next_input = ask_user_for_more_details(unique_symptoms)
if not next_input or not unique_symptoms:
break
for symptom in next_input.split(','):
initial_submitted_symptoms.append(symptom)
import json, os, sys, re
from naiveBayesClassifier import tokenizer
from naiveBayesClassifier.trainer import Trainer
from naiveBayesClassifier.classifier import Classifier
DiseaseClassifier = Trainer(tokenizer)
with open("Dataset.csv", "r") as file:
for i in file:
lines = file.next().split(",")
DiseaseClassifier.train(lines[1], lines[0])
DiseaseClassifier = Classifier(DiseaseClassifier.data, tokenizer)
Classification = DiseaseClassifier.classify(sys.argv[1])
print Classification[0]
