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

Merge branch 'master' of https://git.triton.fet.at/git/service_mail

Browse Source
This commit is contained in:
andis
2017-08-11 18:05:38 +02:00
parent e9da8cb5b0 ba6add107c
commit 9882fba6f3
22 changed files with 250 additions and 283 deletions
Download Patch File Download Diff File Expand all files Collapse all files

184
classifier.py
View File

@@ -1,184 +0,0 @@
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.naive_bayes import MultinomialNB
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
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}
def store_training_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):
train[i]={}
if not key is None and type(train[i]) is dict:
if not type(d) is data_types[key]:
# print str(type(d)) + " vs " + str(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
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"):
t_a=[]
d_a=[]
d_a2=[]
for i in train:
t=db_session.query(MailThread).filter(MailThread.firstmail==i).first()
if not t is None: # Thread muss in der Datenbank sein
if train[i].has_key(key): # In den Trainingsdaten muss der relevante Key sein
t_a.append(t)
d_a.append(train[i][key])
le=LabelEncoder()
d_a2=le.fit_transform(d_a)
return (t_a,d_a2,le)
def in_training(i, key="answered"):
return train.has_key(i) and train[i].has_key(key)
def print_answers(l):
cc=l.classes_
c_id=l.transform(cc)
for i,c in enumerate(cc):
print str(i) + ": " + str(c)
return None
class ThreadDictExtractor(BaseEstimator, TransformerMixin):
def fit(self, x, y=None):
return self
def transform(self, X,y=None):
return [t.mail_flat_dict() for t in X]
class ThreadSubjectExtractor(BaseEstimator, TransformerMixin):
def fit(self, x, y=None):
return self
def transform(self, X,y=None):
return [t.subject() for t in X]
class ThreadTextExtractor(BaseEstimator, TransformerMixin):
def fit(self, x, y=None):
return self
def transform(self, X,y=None):
return [t.text() for t in X]
def build_pipe(p=b"pipe1"):
if p == "pipe1":
p=Pipeline([('tde', ThreadDictExtractor()),
('dv',DictVectorizer()),
('clf', MultinomialNB())
])
elif p=="pipe2":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('text', Pipeline([('tte',ThreadTextExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('envelope', Pipeline([('tde', ThreadDictExtractor()),
('dv',DictVectorizer())
]))
], transformer_weights={
'subject': 1,
'text': 0.7,
'envelope': 0.7
} )),
('clf', MultinomialNB())
])
elif p=="pipe2b":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('text', Pipeline([('tte',ThreadTextExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('envelope', Pipeline([('tde', ThreadDictExtractor()),
('dv',DictVectorizer())
]))
], transformer_weights={
'subject': 1,
'text': 0.7,
'envelope': 0.7
} )),
('mlc', MLPClassifier())
])
elif p=="pipe2c":
p = Pipeline([
('union', FeatureUnion(transformer_list=[
('subject', Pipeline([('tse', ThreadSubjectExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('text', Pipeline([('tte',ThreadTextExtractor()),
('cv',CountVectorizer()),
('tfidf', TfidfTransformer())
])),
('envelope', Pipeline([('tde', ThreadDictExtractor()),
('dv',DictVectorizer())
]))
], transformer_weights={
'subject': 1,
'text': 1,
'envelope': 0.4
} )),
('mlc', MLPClassifier())
])
else:
raise ValueError("The pipe %s is not a valid pipe")
return p
def get_pipe(p=b"pipe1",k=b"answered"):
p=build_pipe(p)
tt= get_training_threads(k)
p.fit(tt[0],tt[1])
return p,tt[2]
from sklearn.metrics import accuracy_score
def test_pipe(pp,k):
tt= get_training_threads(k)
X_train,X_test,y_train,y_test=train_test_split(tt[0],tt[1],test_size=0.2)
if type(pp) is list:
for p in pp:
print "pipe: %s" % p
p=build_pipe(p)
p.fit(X_train,y_train)
ypred=p.predict(X_test)
print accuracy_score(y_test,ypred)
#pipe1=get_pipe("pipe1", "answered")
#pipe2=get_pipe("pipe2", "maintopic")
#pipe2b=get_pipe("pipe2b", "maintopic")

2
classifier/classifier.py
View File

@@ -102,7 +102,7 @@ def get_pipe(p=b"pipe1",k=b"answered"):
def test_pipe(pp,k):
tt= get_training_threads(k)
X_train,X_test,y_train,y_test=train_test_split(tt[0],tt[1],test_size=0.2)
X_train,X_test,y_train,y_test=train_test_split(tt[0],tt[1],test_size=0.4)
if type(pp) is list:
for p in pp:
print "pipe: %s" % p

25
classify_mail.py
View File

@@ -1,25 +0,0 @@
from sklearn.feature_extraction.text import TfidfTransformer,CountVectorizer
from sklearn.feature_extraction import DictVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline, FeatureUnion
import sys
import yaml
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import LabelEncoder
text_clf = Pipeline([('vect', CountVectorizer()),('tfidf', TfidfTransformer()),('clf', MultinomialNB())])
text_ohc = Pipeline([('ohc', OneHotEncoder()),('clf', MultinomialNB())])
combined_features = FeatureUnion([('vect1', CountVectorizer()),('vect2', CountVectorizer())])
enc=OneHotEncoder()
with open("example_1.yaml", 'r') as stream:
try:
train=yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
tc=text_clf.fit(train["data"],train["target"])

42
classify_text.py
View File

@@ -1,42 +0,0 @@
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
text_clf = Pipeline([('vect', CountVectorizer()),('tfidf', TfidfTransformer()),('clf', MultinomialNB())])
import sys
import yaml
with open("example_1.yaml", 'r') as stream:
try:
train=yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
tc=text_clf.fit(train["data"],train["target"])
print(sys.argv[1])
answ=(tc.predict([sys.argv[1]]))[0]
print train["target_names"][answ]
for i in range(0, (len(train["target_names"]))):
print (str(i)+" "+ train["target_names"][i])
ca=int(raw_input("Correct answer.."))
if ca == answ:
print ("Yes I got it right")
else:
print("should I remember this?")
a=raw_input("shoudIrememberthis?")
if a == "y":
train["data"].append(sys.argv[1])
train["target"].append(ca)
print yaml.dump(train,default_flow_style=False)
file=open("example_1.yaml","w")
file.write(yaml.dump(train,default_flow_style=False))
file.close()
else:
print ("Ok, I already forgot")

7
data.yml
View File

@@ -7,9 +7,10 @@
27171: {maintopic: ausleihen}, 27178: {maintopic: studium}, 27182: {maintopic: studium},
27197: {maintopic: information}, 27201: {maintopic: information}, 27218: {maintopic: information},
27219: {maintopic: studium}, 27222: {maintopic: information}, 27226: {maintopic: ausleihen},
27420: {answered: true, maintopic: studium}, 27422: {answered: true, maintopic: studium},
27425: {answered: false, maintopic: studium}, 27431: {answered: false, maintopic: information},
27434: {answered: false, lang: de, maintopic: information}, 27435: {answered: false},
27263: {maintopic: ausleihen}, 27267: {maintopic: ausleihen}, 27420: {answered: true,
maintopic: studium}, 27422: {answered: true, maintopic: studium}, 27425: {answered: false,
maintopic: studium}, 27431: {answered: false, maintopic: information}, 27434: {
answered: false, lang: de, maintopic: information}, 27435: {answered: false},
27438: {answered: false, maintopic: information}, 27439: {answered: true, maintopic: studium},
27441: {answered: false, maintopic: studium}, 27444: {answered: true, maintopic: ausleihen},
27454: {answered: false, maintopic: information}, 27455: {answered: false, maintopic: information},

35
db_model_version_1.py Normal file
View File

@@ -0,0 +1,35 @@
## File autogenerated by genmodel.py
from sqlalchemy import *
meta = MetaData()
mails = Table('mails', meta,
Column('created_at', TIMESTAMP, nullable=False),
Column('updated_at', TIMESTAMP, nullable=False),
Column('id', INTEGER, primary_key=True, nullable=False),
Column('date', DATETIME),
Column('envelope', TEXT),
Column('body', TEXT),
Column('text', TEXT),
Column('from_', TEXT),
Column('from_mailbox', VARCHAR),
Column('from_host', VARCHAR),
Column('to_', TEXT),
Column('to_mailbox', TEXT),
Column('to_host', VARCHAR),
Column('subject', TEXT),
)
threads = Table('threads', meta,
Column('created_at', TIMESTAMP, nullable=False),
Column('updated_at', TIMESTAMP, nullable=False),
Column('id', INTEGER, primary_key=True, nullable=False),
Column('firstmail', INTEGER),
Column('islabeled', BOOLEAN),
Column('opened', BOOLEAN),
Column('body', TEXT),
)

4
db_repository/README Normal file
View File

@@ -0,0 +1,4 @@
This is a database migration repository.
More information at
http://code.google.com/p/sqlalchemy-migrate/

0
db_repository/__init__.py Normal file
View File

6
db_repository/manage.py Normal file
View File

@@ -0,0 +1,6 @@
#!.env/bin/python
from migrate.versioning.shell import main
import storage
if __name__ == '__main__':
main(debug='False')

25
db_repository/migrate.cfg Normal file
View File

@@ -0,0 +1,25 @@
[db_settings]
# Used to identify which repository this database is versioned under.
# You can use the name of your project.
repository_id=service mail db repository
# The name of the database table used to track the schema version.
# This name shouldn't already be used by your project.
# If this is changed once a database is under version control, you'll need to
# change the table name in each database too.
version_table=migrate_version
# When committing a change script, Migrate will attempt to generate the
# sql for all supported databases; normally, if one of them fails - probably
# because you don't have that database installed - it is ignored and the
# commit continues, perhaps ending successfully.
# Databases in this list MUST compile successfully during a commit, or the
# entire commit will fail. List the databases your application will actually
# be using to ensure your updates to that database work properly.
# This must be a list; example: ['postgres','sqlite']
required_dbs=[]
# When creating new change scripts, Migrate will stamp the new script with
# a version number. By default this is latest_version + 1. You can set this
# to 'true' to tell Migrate to use the UTC timestamp instead.
use_timestamp_numbering=False

1
db_repository/storage Symbolic link
View File

@@ -0,0 +1 @@
storage

33
db_repository/versions/002_add_date_to_threads.py Normal file
View File

@@ -0,0 +1,33 @@
from sqlalchemy import *
from migrate import *
from migrate.changeset import schema
pre_meta = MetaData()
post_meta = MetaData()
threads = Table('threads', post_meta,
Column('created_at', TIMESTAMP, nullable=False),
Column('updated_at', TIMESTAMP, nullable=False),
Column('id', Integer, primary_key=True, nullable=False),
Column('firstmail', Integer),
Column('date', DateTime),
Column('islabeled', Boolean),
Column('opened', Boolean),
Column('body', Text),
)
def upgrade(migrate_engine):
# Upgrade operations go here. Don't create your own engine; bind
# migrate_engine to your metadata
pre_meta.bind = migrate_engine
post_meta.bind = migrate_engine
post_meta.tables['threads'].columns['date'].create()
def downgrade(migrate_engine):
# Operations to reverse the above upgrade go here.
pre_meta.bind = migrate_engine
post_meta.bind = migrate_engine
post_meta.tables['threads'].columns['date'].drop()

34
db_repository/versions/003_maintopic.py Normal file
View File

@@ -0,0 +1,34 @@
from sqlalchemy import *
from migrate import *
from migrate.changeset import schema
pre_meta = MetaData()
post_meta = MetaData()
threads = Table('threads', post_meta,
Column('created_at', TIMESTAMP, nullable=False),
Column('updated_at', TIMESTAMP, nullable=False),
Column('id', Integer, primary_key=True, nullable=False),
Column('firstmail', Integer),
Column('date', DateTime),
Column('islabeled', Boolean),
Column('opened', Boolean),
Column('body', Text),
Column('maintopic', String),
)
def upgrade(migrate_engine):
# Upgrade operations go here. Don't create your own engine; bind
# migrate_engine to your metadata
pre_meta.bind = migrate_engine
post_meta.bind = migrate_engine
post_meta.tables['threads'].columns['maintopic'].create()
def downgrade(migrate_engine):
# Operations to reverse the above upgrade go here.
pre_meta.bind = migrate_engine
post_meta.bind = migrate_engine
post_meta.tables['threads'].columns['maintopic'].drop()

0
db_repository/versions/__init__.py Normal file
View File

39
flaskapp/__init__.py
View File

@@ -5,7 +5,7 @@ from flask import Flask,jsonify,send_from_directory, render_template
from config import Config
import yaml
import os
from sqlalchemy import desc
from storage import MailThread,db_session
app = Flask(__name__, template_folder="templates", static_folder="static")
@@ -20,20 +20,35 @@ def render_index(mths,code=200):
), code
from classifier import get_pipe
mail_threads=db_session.query(MailThread).all()
pipe1,le=get_pipe("pipe1",b"answered")
pipe2,le2=get_pipe("pipe2b", b"maintopic")
pipe3,le3=get_pipe("pipe2b", b"lang")
#pipe1,le=get_pipe("pipe1",b"answered")
#pipe2,le2=get_pipe("pipe2b", b"maintopic")
#pipe3,le3=get_pipe("pipe2b", b"lang")
answered=le.inverse_transform(pipe1.predict(mail_threads))
maintopic=le2.inverse_transform(pipe2.predict(mail_threads))
lang=le3.inverse_transform(pipe3.predict(mail_threads))
#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=answered[i]
# t.maintopic=maintopic[i]
# t.lang=lang[i]
for i, t in enumerate(mail_threads):
t.answered=answered[i]
t.maintopic=maintopic[i]
t.lang=lang[i]
@app.route("/")
def hello():
mth=mail_threads
mth=db_session.query(MailThread).order_by(desc(MailThread.date)).all()
return render_index(mth)
@app.route("/answered/<id>/<value>")
def store_answered(id, value):
mth=db_session.query(MailThread).filter(MailThread.firstmail==int(id)).first()
value= value in ["true", "True", "1", "t"]
mth.answered=bool(value)
mth.opened=bool(value)
return render_index([mth])
@app.route("/studium")
def studium():
mth=db_session.query(MailThread).filter(MailThread.maintopic=="studium").order_by(desc(MailThread.date)).all()
return render_index(mth)

11
flaskapp/templates/index.html
View File

@@ -6,6 +6,11 @@
<script src="static/bootstrap/js/bootstrap.min.js" ></script>
</head>
<body>
<style>
.card.opened-True {
background: lightgreen;
}
</style>
<div class="container">
<div class="row">
<div class="col-12">
@@ -14,7 +19,7 @@
<div id="accordion" role="tablist" aria-multiselectable="true">
{% for m in mths %}
<div class="card" style="padding-top: 2pt; padding-bottom:2pt; border-radius:0;margin-top:1pt; margin-bottom:1pt">
<div class="card opened-{{m.opened}}" style="padding-top: 2pt; padding-bottom:2pt; border-radius:0;margin-top:1pt; margin-bottom:1pt">
<div class="" role="tab" id="heading{{m.firstmail}}">
<b class="mb-0">
<a data-toggle="collapse" data-parent="#accordion" href="#collapse{{m.firstmail}}" aria-expanded="true" aria-controls="collapse1">
@@ -26,7 +31,7 @@
<div id="collapse{{m.firstmail}}" class="collapse" role="tabpanel" aria-labelledby="headingOne">
<div class="card-block">
<div style="white-space: pre-wrap;font:Courier, monospace; font-size:small; width:50em; border: thin blue solid;"> {{ m.text() }} </div>
<div style="white-space: pre-wrap;font:Courier, monospace; font-size:small; width:50em; border: thin blue solid;"> {{ m.print_text() }} </div>
</div>
</div>
</div>
@@ -36,7 +41,7 @@
{% for m in mths %}
ID: {{m.tstr()}}
{{ m.text() }}
{{ m.print_text() }}
{% endfor %}
</div>

6
migration.py Executable file
View File

@@ -0,0 +1,6 @@
#!.env/bin/python
from migrate.versioning.shell import main
import storage
if __name__ == '__main__':
main(debug='False',repository="db_repository", url="sqlite:///test.sqlite")

22
run.py
View File

@@ -16,7 +16,6 @@ from storage import Mail, MailThread, db_session
#import yaml
#import email
from classifier import get_training_threads, print_answers, in_training, store_training_data, get_pipe, test_pipe, train_single_thread # , pipe2, pipe2b
from flaskapp import app
def predict_thread(p,l,t):
@@ -27,10 +26,31 @@ def predict_thread(p,l,t):
#print "arg1:"+sys.argv[1]
if len(sys.argv)>1:
if sys.argv[1] == "fetch_threads":
print flatten_threads(fetch_threads())
if sys.argv[1] == "predict_threads":
pipe1,le=get_pipe("pipe1",b"answered")
pipe2,le2=get_pipe("pipe2b", b"maintopic")
pipe3,le3=get_pipe("pipe2b", b"lang")
mail_threads=db_session.query(MailThread).all()
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=answered[i]
t.opened=answered[i]
t.maintopic=maintopic[i]
t.lang=lang[i]
db_session.add(t)
db_session.commit()
if sys.argv[1] == "run_server":
from flaskapp import app
app.run(port=3000,debug=True)
if sys.argv[1] == "print_threads":

2
storage/__init__.py
View File

@@ -1,3 +1,5 @@
from database import db_session, init_db
from mail_model import Mail
from thread_model import MailThread
from database import Base
metadata=Base.metadata

2
storage/mail_model.py
View File

@@ -75,6 +75,8 @@ class Mail(Base):
from_array=[]
# print "Status"
# print env
if not env.date is None:
self.date=env.date
if not env.to is None:
for t in env.to:
a={"host": t.host, "mail": t.mailbox}

37
storage/thread_model.py
View File

@@ -23,15 +23,17 @@ class MailThread(Base):
__tablename__ = 'threads'
id = Column(Integer, primary_key=True)
firstmail = Column(Integer)
date = Column(DateTime)
islabeled = Column(Boolean)
opened = Column(Boolean)
body = Column(Text)
maintopic=Column(String)
__schema__=FullThreadSchema
__jsonid__='thread'
__whiteattrs__= ["body"]
__jsonattrs__=None
answered=False
maintopic="information"
# maintopic="information"
lang=""
def bdy(self):
return yaml.load(self.body)
@@ -51,7 +53,7 @@ class MailThread(Base):
def tstr(self):
fr=yaml.load(self.mails()[0].from_)
return "(" + str(self.answered)+ ", "+ str(self.maintopic)+ ", "+ str(self.lang) + ") " + str(self.firstmail)+": "+str(fr[0]["mail"])+"@"+str(fr[0]["host"]) + " | ".join(yaml.load(self.mails()[0].subject))
return "(" + str(self.opened)+ ", "+ str(self.maintopic)+ ", "+ str(self.lang) + ") " + str(self.firstmail)+": "+str(fr[0]["mail"])+"@"+str(fr[0]["host"]) + " | ".join(yaml.load(self.mails()[0].subject))
def mails(self):
a=[]
@@ -94,7 +96,34 @@ class MailThread(Base):
m.compile_text()
db_session.add(m)
db_session.commit()
self.date=self.mails()[0].date
def print_text(self,filter="all"):
a=u""
def mail_txt(m):
#txt ="Gesendet von: "+ str(m.from_mailbox)+"@"+str(m.from_host) +"\n"
txt=""
fr=yaml.load(m.from_)
txt= txt+ "Gesendet von: "+str(fr[0]["mail"])+"@"+str(fr[0]["host"])+" am "+ str(m.date) + "\n"
t=yaml.load(m.text)
if type(t) is unicode:
#txt=txt
txt=txt+t
else:
t=t.decode("ISO-8859-1")
txt=txt+t
return txt
if filter=="all":
mm=self.mails()
for m in mm:
a=a+mail_txt(m)+"\n****........................................***\n"
elif filter=="first":
a=mail_txt(m[0])
a=re.sub(r'\n\s*\n',r'\n',a)
a=re.sub(r'<!--.*-->',r'',a,flags=re.MULTILINE|re.DOTALL)
a=re.sub(r'\s*>+ .*\n',r'',a)
return a
def text(self,filter="all"):
a=u""
def mail_txt(m):
@@ -108,11 +137,11 @@ class MailThread(Base):
mm=self.mails()
if filter=="all":
for m in mm:
a=a+mail_txt(m)+"****........................................***\n"
a=a+mail_txt(m)+"\n****........................................***\n"
elif filter=="first":
a=mail_txt(m[0])
a=re.sub(r'\n\s*\n',r'\n',a)
# a=re.sub(r'<!--.*-->',r'',a,flags=re.MULTILINE|re.DOTALL)
a=re.sub(r'<!--.*-->',r'',a,flags=re.MULTILINE|re.DOTALL)
a=re.sub(r'\s*>+ .*\n',r'',a)

BIN
test.sqlite
View File

Binary file not shown.