diff --git a/nlp/__init__.py b/nlp/__init__.py
deleted file mode 100644
index db614b4..0000000
--- a/nlp/__init__.py
+++ /dev/null
@@ -1,46 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Top-level package for nlp."""
-
-__author__ = """A Student"""
-__email__ = 'student@example.com'
-__version__ = '0.1.0'
-
-# -*- coding: utf-8 -*-
-import configparser
-import os
-
-# ~/.nlp/nlp.cfg will contain configuration information for the project,
-# such as where data will be downloaded from.
-# here is an example.
-def write_default_config(path):
- w = open(path, 'wt')
- w.write('[data]\n')
- w.write('url = https://www.dropbox.com/s/o0nxd8pnwy809u2/headlines.csv?dl=1\n')
- w.write('file = %s%s%s\n' % (nlp_path, os.path.sep, 'headlines.csv'))
- w.close()
-
-# Find NLP_HOME path
-if 'NLP_HOME' in os.environ:
- nlp_path = os.environ['NLP_HOME']
-else:
- nlp_path = os.environ['HOME'] + os.path.sep + '.nlp' + os.path.sep
-
-# Make nlp directory if not present
-try:
- os.makedirs(nlp_path)
-except:
- pass
-
-# main config file.
-config_path = nlp_path + 'nlp.cfg'
-# classifier
-clf_path = nlp_path + 'clf.pkl'
-
-# write default config if not present.
-if not os.path.isfile(config_path):
- write_default_config(config_path)
-
-# config variable now accessible throughout project.
-config = configparser.RawConfigParser()
-config.read(config_path)
\ No newline at end of file
diff --git a/nlp/app/__init__.py b/nlp/app/__init__.py
deleted file mode 100644
index 8c02e85..0000000
--- a/nlp/app/__init__.py
+++ /dev/null
@@ -1,7 +0,0 @@
-from flask import Flask
-import os
-from .. import nlp_path
-app = Flask(__name__)
-app.config['SECRET_KEY'] = 'you-will-never-guess' # for CSRF
-
-from . import routes
\ No newline at end of file
diff --git a/nlp/app/forms.py b/nlp/app/forms.py
deleted file mode 100644
index 5395597..0000000
--- a/nlp/app/forms.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from flask_wtf import FlaskForm
-from wtforms import StringField, SubmitField
-from wtforms.validators import DataRequired
-
-class MyForm(FlaskForm):
- class Meta: # Ignoring CSRF security feature.
- csrf = False
-
- input_field = StringField(label='input headline:', id='input_field',
- validators=[DataRequired()],
- render_kw={'style': 'width:50%'})
- submit = SubmitField('Submit')
\ No newline at end of file
diff --git a/nlp/app/routes.py b/nlp/app/routes.py
deleted file mode 100644
index ec4db3f..0000000
--- a/nlp/app/routes.py
+++ /dev/null
@@ -1,28 +0,0 @@
-from flask import render_template, flash, redirect, session
-from . import app
-from .forms import MyForm
-from .. import clf_path
-
-import pickle
-import sys
-
-clf, vec = pickle.load(open(clf_path, 'rb'))
-print('read clf %s' % str(clf))
-print('read vec %s' % str(vec))
-labels = ['liberal', 'conservative']
-
-@app.route('/', methods=['GET', 'POST'])
-@app.route('/index', methods=['GET', 'POST'])
-def index():
- form = MyForm()
- result = None
- if form.validate_on_submit():
- input_field = form.input_field.data
- X = vec.transform([input_field])
- pred = clf.predict(X)[0]
- proba = clf.predict_proba(X)[0].max()
- # flash(input_field)
- return render_template('myform.html', title='', form=form,
- prediction=labels[pred], confidence='%.2f' % proba)
- #return redirect('/index')
- return render_template('myform.html', title='', form=form, prediction=None, confidence=None)
diff --git a/nlp/app/static/__init__.py b/nlp/app/static/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/nlp/app/static/main.css b/nlp/app/static/main.css
deleted file mode 100644
index 3277346..0000000
--- a/nlp/app/static/main.css
+++ /dev/null
@@ -1,20 +0,0 @@
-body {
- margin: 50px;
- padding: 50px;
- font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;
- color: #444;
-}
-/*
- * Formatting the header area
- */
-header {
- background-color: #DFB887;
- height: 35px;
- width: 100%;
- opacity: .9;
- margin-bottom: 10px;
-}
-
-label {
- color: black;
-}
\ No newline at end of file
diff --git a/nlp/app/templates/__init__.py b/nlp/app/templates/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/nlp/app/templates/base.html b/nlp/app/templates/base.html
deleted file mode 100644
index d747410..0000000
--- a/nlp/app/templates/base.html
+++ /dev/null
@@ -1,34 +0,0 @@
-
-
- {% if title %}
- {{ title }} - nlp
- {% else %}
- nlp
- {% endif %}
-
-
-
- my nlp project
-
- {% if form.errors %}
- {{ form.errors }}
- {% endif %}
-
- {% block content %}{% endblock %}
- {% if confidence %}
-
- Prediction = {{ prediction }}
Confidence = {{ confidence }}
-
- {% endif %}
- {% with messages = get_flashed_messages() %}
- {% if messages %}
-
- {% for message in messages %}
- - {{ message }}
- {% endfor %}
-
- {% endif %}
- {% endwith %}
-
-
-
\ No newline at end of file
diff --git a/nlp/app/templates/myform.html b/nlp/app/templates/myform.html
deleted file mode 100644
index c39a643..0000000
--- a/nlp/app/templates/myform.html
+++ /dev/null
@@ -1,11 +0,0 @@
-{% extends "base.html" %}
-
-{% block content %}
- Partisan headline classifier
-
-{% endblock %}
\ No newline at end of file
diff --git a/nlp/cli.py b/nlp/cli.py
deleted file mode 100644
index 15d9be4..0000000
--- a/nlp/cli.py
+++ /dev/null
@@ -1,98 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Demonstrating a very simple NLP project. Yours should be more exciting than this."""
-import click
-import glob
-import pickle
-import sys
-
-import numpy as np
-import pandas as pd
-import re
-import requests
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.linear_model import LogisticRegression
-from sklearn.model_selection import StratifiedKFold
-from sklearn.metrics import accuracy_score, classification_report
-
-from . import clf_path, config
-
-@click.group()
-def main(args=None):
- """Console script for nlp."""
- return 0
-
-@main.command('web')
-@click.option('-p', '--port', required=False, default=5000, show_default=True, help='port of web server')
-def web(port):
- """
- Launch the flask web app.
- """
- from .app import app
- app.run(host='0.0.0.0', debug=True, port=port)
-
-@main.command('dl-data')
-def dl_data():
- """
- Download training/testing data.
- """
- data_url = config.get('data', 'url')
- data_file = config.get('data', 'file')
- print('downloading from %s to %s' % (data_url, data_file))
- r = requests.get(data_url)
- with open(data_file, 'wt') as f:
- f.write(r.text)
-
-
-def data2df():
- return pd.read_csv(config.get('data', 'file'))
-
-@main.command('stats')
-def stats():
- """
- Read the data files and print interesting statistics.
- """
- df = data2df()
- print('%d rows' % len(df))
- print('label counts:')
- print(df.partisan.value_counts())
-
-@main.command('train')
-def train():
- """
- Train a classifier and save it.
- """
- # (1) Read the data...
- df = data2df()
- # (2) Create classifier and vectorizer.
- clf = LogisticRegression(max_iter=1000, C=1, class_weight='balanced')
- vec = CountVectorizer(min_df=5, ngram_range=(1,3), binary=True, stop_words='english')
- X = vec.fit_transform(df.title)
- y = df.partisan.values
- # (3) do cross-validation and print out validation metrics
- # (classification_report)
- do_cross_validation(clf, X, y)
- # (4) Finally, train on ALL data one final time and
- # train. Save the classifier to disk.
- clf.fit(X, y)
- pickle.dump((clf, vec), open(clf_path, 'wb'))
- top_coef(clf, vec)
-
-def do_cross_validation(clf, X, y):
- all_preds = np.zeros(len(y))
- for train, test in StratifiedKFold(n_splits=5, shuffle=True, random_state=42).split(X,y):
- clf.fit(X[train], y[train])
- all_preds[test] = clf.predict(X[test])
- print(classification_report(y, all_preds))
-
-def top_coef(clf, vec, labels=['liberal', 'conservative'], n=10):
- feats = np.array(vec.get_feature_names_out())
- print('top coef for %s' % labels[1])
- for i in np.argsort(clf.coef_[0])[::-1][:n]:
- print('%20s\t%.2f' % (feats[i], clf.coef_[0][i]))
- print('\n\ntop coef for %s' % labels[0])
- for i in np.argsort(clf.coef_[0])[:n]:
- print('%20s\t%.2f' % (feats[i], clf.coef_[0][i]))
-
-if __name__ == "__main__":
- sys.exit(main())
diff --git a/nlp/nlp.py b/nlp/nlp.py
deleted file mode 100644
index 7fbbae4..0000000
--- a/nlp/nlp.py
+++ /dev/null
@@ -1,3 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Main module."""