bofh/service_mail
9
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

refactor1

Browse Source
This commit is contained in:
Andreas Stephanides
2017-08-28 09:08:47 +02:00
parent 699f4f6546
commit 630b982502
14 changed files with 274 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
classifier/__init__.py
View File

@@ -1,6 +1,7 @@
from classifier import in_training, print_answers
from classifier import print_answers
from classifier import get_pipe, test_pipe, get_training_threads
from classifier import store_training_data
#from classifier import store_training_data
#in_training,
from training import train_single_thread

117
classifier/classifier.py
View File

@@ -8,88 +8,18 @@ from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
import numpy as np
import yaml
from storage import MailThread,db_session
from sklearn.metrics import accuracy_score, confusion_matrix
from collections import namedtuple
from storage import get_training_threads #MailThread,db_session
#with open("data.yml", 'r') as stream:
# try:
# train=yaml.load(stream)
# except yaml.YAMLError as exc:
# print(exc)
data_types= { "answered": bool, "maintopic": str, "lang": str}
def set_train_data(i,d,key=b"answered"):
global train
#------------------------------------
if not data_types.has_key(key):
raise ValueError("Key "+str(key)+" unknown")
if not train.has_key(i) or train[i] is None:
train[i]={}
if not type(d) is data_types[key]:
raise TypeError("Data - %s - for key "% d +str(key)+" must be " +str(data_types[key])+ " but it is "+ str(type(d)))
#------------------------------------
train[i][key]=d
def store_training_data(i, d,key=b"answered"):
set_train_data(i,d,key)
with open("data.yml","w") as file:
file.write(yaml.dump(train,default_flow_style=True))
file.close()
# Lade Trainingsdaten fuer einen angegebenen key (Label/Eigenschaft)
def get_training_threads(key="answered", filters=[]):
if not data_types.has_key(key):
raise ValueError("Key "+str(key)+" unknown")
#------------------------------------
t_a=[]
d_a=[]
d_a2=[]
#------------------------------------
if "db" in filters:
q=db_session.query(MailThread).filter(MailThread.istrained.is_(True))
if "de" in filters:
q=q.filter(MailThread.lang=="de")
elif "en" in filters:
q=q.filter(MailThread.lang=="en")
tt=q.all()
for t in tt:
t_a.append(t)
if key =="answered":
d_a.append(t.is_answered())
elif key=="maintopic":
d_a.append(t.maintopic)
elif key=="lang":
d_a.append(t.lang)
else:
raise ValueError("Database Filter now required")
le=LabelEncoder()
d_a2=le.fit_transform(d_a)
return (t_a,d_a2,le)
# else:
# for i in train:
# if train[i].has_key(key): # In den Trainingsdaten muss der relevante Key sein
# t=db_session.query(MailThread).filter(MailThread.firstmail==i).first#()
# if not t is None: # Thread muss in der Datenbank sein
# t_a.append(t)
# d_a.append(train[i][key])
def in_training(i, key="answered"):
return train.has_key(i) and train[i].has_key(key)
PredictTool=namedtuple("PredictTool",["Pipeline","LabelEncoder"])
def print_answers(l):
cc=l.classes_
c_id=l.transform(cc)
for i,c in enumerate(cc):
print str(i) + ": " + str(c)
classes=l.classes_
classes_encoded=l.transform(cc)
for i, c in zip(classes_encoded,classes):
print str(i) + ": " + str(c)
return None
@@ -117,15 +47,14 @@ class ThreadFirstTextExtractor(BaseEstimator, TransformerMixin):
def transform(self, X,y=None):
return [t.text("first") for t in X]
def get_pipe(p=b"pipe1",k=b"answered",filters=[]):
def get_pipe(p=b"pipe1",key=b"answered",filters=["db"]):
p=build_pipe(p)
tt= get_training_threads(k,filters)
#print tt
if len(tt[0]) > 0:
p.fit(tt[0],tt[1])
return p,tt[2]
threads, labels, labelenc= get_training_threads(key,filters)
if len(threads) > 0:
p.fit(threads,labels)
return PredictTool(p,labelenc)
else:
return None, None
return PredictTool(None, None)
def test_pipe(pp,k,f=[]):
tt= get_training_threads(k,f)
@@ -142,13 +71,13 @@ def test_pipe(pp,k,f=[]):
def build_pipe(p=b"pipe1"):
if p == "pipe1":
def build_pipe(pipe=b"pipe1"):
if pipe == "pipe1":
p=Pipeline([('tde', ThreadDictExtractor()),
('dv',DictVectorizer()),
('clf', MultinomialNB())
])
elif p=="pipe2":
elif pipe=="pipe2":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -169,7 +98,7 @@ def build_pipe(p=b"pipe1"):
} )),
('clf', MultinomialNB())
])
elif p=="pipe2b":
elif pipe=="pipe2b":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -190,7 +119,7 @@ def build_pipe(p=b"pipe1"):
} )),
('mlc', MLPClassifier())
])
elif p=="pipe2d":
elif pipe=="pipe2d":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -217,7 +146,7 @@ def build_pipe(p=b"pipe1"):
('mlc', MLPClassifier())
])
elif p=="pipe2e":
elif pipe=="pipe2e":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -243,7 +172,7 @@ def build_pipe(p=b"pipe1"):
} )),
('mlc', MLPClassifier(hidden_layer_sizes=(100,100)))
])
elif p=="pipe2e1":
elif pipe=="pipe2e1":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -269,7 +198,7 @@ def build_pipe(p=b"pipe1"):
} )),
('mlc', MLPClassifier(hidden_layer_sizes=(100,100,50)))
])
elif p=="pipe2f":
elif pipe=="pipe2f":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -295,7 +224,7 @@ def build_pipe(p=b"pipe1"):
} )),
('mlc', MLPClassifier(hidden_layer_sizes=(100,100)))
])
elif p=="pipe2g":
elif pipe=="pipe2g":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
@@ -321,7 +250,7 @@ def build_pipe(p=b"pipe1"):
} )),
('mlc', MLPClassifier(hidden_layer_sizes=(100,100,100)))
])
elif p=="pipe2c":
elif pipe=="pipe2c":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),

23
classifier/oldstuff.py Normal file
View File

@@ -0,0 +1,23 @@
def set_train_data(i,d,key=b"answered"):
global train
#------------------------------------
if not data_types.has_key(key):
raise ValueError("Key "+str(key)+" unknown")
if not train.has_key(i) or train[i] is None:
train[i]={}
if not type(d) is data_types[key]:
raise TypeError("Data - %s - for key "% d +str(key)+" must be " +str(data_types[key])+ " but it is "+ str(type(d)))
#------------------------------------
train[i][key]=d
def store_training_data(i, d,key=b"answered"):
set_train_data(i,d,key)
with open("data.yml","w") as file:
file.write(yaml.dump(train,default_flow_style=True))
file.close()
def in_training(i, key="answered"):
return train.has_key(i) and train[i].has_key(key)
data_types= { "answered": bool, "maintopic": str, "lang": str}

23
classifier/prediction.py
View File

@@ -1,22 +1,31 @@
from classifier import get_training_threads, print_answers, in_training, store_training_data, get_pipe
from classifier import get_pipe
from storage import db_session, MailThread
def predict_threads():
pipe1,le=get_pipe("pipe1",b"answered",["db"])
"""
Predicts the language, topic and if a thread is anwered and writes that to the database. This function doesn't have a return value.
"""
# Loading pipes for the prediction of each thread
pipe1,le=get_pipe("pipe1",key=b"answered",filter=["db"])
pipe2,le2=get_pipe("pipe2g", b"maintopic",["db"])
pipe3,le3=get_pipe("pipe2b", b"lang",["db"])
# Loading untrained MailThreads:
q=db_session.query(MailThread).filter(MailThread.istrained.op("IS NOT")(True))
mail_threads=q.all()
if len(mail_threads) ==0:
raise ValueError("no untrained threads found")
raise StandardError("no untrained threads found in database")
answered=le.inverse_transform(pipe1.predict(mail_threads))
maintopic=le2.inverse_transform(pipe2.predict(mail_threads))
lang=le3.inverse_transform(pipe3.predict(mail_threads))
for i, t in enumerate(mail_threads):
t.answered=bool(answered[i])
t.opened=bool(answered[i])
t.maintopic=str(maintopic[i])
t.lang=str(lang[i])
t.answered, t.opened, t.maintopic, t.lang = ( bool(answered[i]),
bool(answered[i]),
str(maintopic[i]),
str(lang[i])
)
db_session.add(t)
db_session.commit()

2
classifier/training.py
View File

@@ -2,7 +2,7 @@ from sklearn.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder
import numpy
from storage import Mail, MailThread, db_session
from classifier import store_training_data, print_answers
from classifier import print_answers