Hola
This commit is contained in:
parent
affbe5570b
commit
539aa9849c
X_test.csvX_train.csv
backup/base
__init__.py
dataset_preprocessed.csvlg.savxgb.savy_test.csvy_train.csv__pycache__
__init__.cpython-310.pycadmin.cpython-310.pycapps.cpython-310.pycmodels.cpython-310.pycurls.cpython-310.pycviews.cpython-310.pyc
admin.pyapps.pyforms.pymigrations
models.pystatic/js
templates/base
tests.pyurls.pyutils.pyviews.py
1199
X_test.csv
1199
X_test.csv
File diff suppressed because it is too large
Load Diff
4789
X_train.csv
4789
X_train.csv
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1,3 +0,0 @@
|
||||
from django.contrib import admin
|
||||
|
||||
# Register your models here.
|
||||
@ -1,6 +0,0 @@
|
||||
from django.apps import AppConfig
|
||||
|
||||
|
||||
class BaseConfig(AppConfig):
|
||||
default_auto_field = 'django.db.models.BigAutoField'
|
||||
name = 'base'
|
||||
@ -1,4 +0,0 @@
|
||||
from django import forms
|
||||
|
||||
class DocumentForm(forms.Form):
|
||||
docfile = forms.FileField(label='Select a file')
|
||||
@ -1,22 +0,0 @@
|
||||
# Generated by Django 5.0.6 on 2024-05-20 15:19
|
||||
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
initial = True
|
||||
|
||||
dependencies = [
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name='Upload',
|
||||
fields=[
|
||||
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
||||
('uploadFile', models.FileField(upload_to='')),
|
||||
('uploadDate', models.DateTimeField(auto_now_add=True)),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -1,23 +0,0 @@
|
||||
# Generated by Django 5.0.6 on 2024-05-20 15:33
|
||||
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
('base', '0001_initial'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name='Document',
|
||||
fields=[
|
||||
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
||||
('docfile', models.FileField(upload_to='documents/%Y/%m/%d')),
|
||||
],
|
||||
),
|
||||
migrations.DeleteModel(
|
||||
name='Upload',
|
||||
),
|
||||
]
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1 +0,0 @@
|
||||
from django.db import models
|
||||
@ -1,7 +0,0 @@
|
||||
$(document).ready( function()
|
||||
{
|
||||
$('#spinner').on('click', function()
|
||||
{
|
||||
$('body').addClass('busy');
|
||||
});
|
||||
});
|
||||
@ -1,128 +0,0 @@
|
||||
{% extends 'main.html' %}
|
||||
|
||||
{% block content %}
|
||||
{% load static %}
|
||||
<div class="container-fluid">
|
||||
<div class="mx-auto p-4 text-center bg-white shadow-sm">
|
||||
<a href="/" >
|
||||
<h1>
|
||||
EXTREMUM
|
||||
</h1>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
<br>
|
||||
<br>
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
<h3>
|
||||
<i class="fas fa-upload"></i> Import a file
|
||||
</h3>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="row">
|
||||
<div class = "mx-auto p-4 text-center">
|
||||
<form action="{% url 'home' %}" id="csv" method="post" enctype="multipart/form-data">
|
||||
{% csrf_token %}
|
||||
<input type="file"
|
||||
title="Upload excel file"
|
||||
name="excel_file"
|
||||
style="border: 1px solid black; padding: 5px;"
|
||||
required="required">
|
||||
<input action="uploadCsv" type="submit" method="POST"
|
||||
value="Upload"
|
||||
name="csv"
|
||||
style="border: 1px solid green; padding:5px; border-radius: 2px; cursor: pointer;">
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<br>
|
||||
<div class="row">
|
||||
<div class="col">
|
||||
<div class="scrollit">
|
||||
{{ data_to_display|safe }}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<br>
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
<h3 >
|
||||
<i class="fa-solid fa-chart-simple"></i> Stats
|
||||
</h3>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
<form action="{% url 'stats' %}" method="POST" id="stats">
|
||||
{% csrf_token %}
|
||||
<select id="feature1" name="feature1">
|
||||
<option disabled selected> Feature 1 </option>
|
||||
{% for label in labels %}
|
||||
<option value={{label}}>{{label}}</option>
|
||||
{% endfor %}
|
||||
</select>
|
||||
<select id="feature2" name="feature2">
|
||||
<option disabled selected> Feature 2 </option>
|
||||
{% for label in labels %}
|
||||
<option value={{label}}>{{label}}</option>
|
||||
{% endfor %}
|
||||
</select>
|
||||
<input type="submit" value="Plot">
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{% if fig %}
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
{{ fig|safe }}
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
<h3 >
|
||||
<i class="fas fa-cog"></i> Preprocessing
|
||||
</h3>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center multi-button">
|
||||
<form action="/preprocess" method="POST">
|
||||
{% csrf_token %}
|
||||
<div class="multi-button">
|
||||
<button type="submit" name = "std" class="button-6" role="button" >Standardization</button>
|
||||
<button type="submit" name="onehot" style="margin:0;margin-left:16px;" class="button-6" role="button" >One Hot Encoding</button>
|
||||
<button type="submit" name="imp" style="margin:0;margin-left:16px;" class="button-6" role="button" >Imputations</button>
|
||||
</div>
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<br>
|
||||
<br>
|
||||
|
||||
<div class="row">
|
||||
<div class="col d-flex justify-content-center">
|
||||
<form action="/train" method="POST">
|
||||
{% csrf_token %}
|
||||
<button type="submit" name = "svm" style="margin:0;margin-left:16px;" class="button-6" role="button" >Support Vector Machine</button>
|
||||
<button type="submit" name = "logit" style="margin:0;margin-left:16px;" class="button-6" role="button" >Logistic Regression</button>
|
||||
<button type="submit" name="xgb" style="margin:0;margin-left:16px;" class="button-6" role="button" >XGBoost</button>
|
||||
<button type="submit" name="dt" style="margin:0;margin-left:16px;" class="button-6" role="button" >Decision Tree</button>
|
||||
<button type="submit" name="rt" style="margin:0;margin-left:16px;" class="button-6" role="button" >Random Forest</button>
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<br>
|
||||
<br>
|
||||
</div>
|
||||
{% endblock content%}
|
||||
@ -1,3 +0,0 @@
|
||||
from django.test import TestCase
|
||||
|
||||
# Create your tests here.
|
||||
@ -1,10 +0,0 @@
|
||||
from django.urls import path
|
||||
from . import views
|
||||
from . import models
|
||||
|
||||
urlpatterns = [
|
||||
path('', views.home, name="home"),
|
||||
path('preprocess', views.preprocess, name="preprocess"),
|
||||
path('stats', views.stats, name="stats"),
|
||||
path('train',views.training, name = 'training'),
|
||||
]
|
||||
@ -1,5 +0,0 @@
|
||||
def stats(feature1, feature2, df):
|
||||
import plotly.express as px
|
||||
fig = px.scatter(df, x=feature1, y=feature2, color='Churn')
|
||||
fig = fig.to_html(full_html=False)
|
||||
return fig
|
||||
@ -1,131 +0,0 @@
|
||||
from django.shortcuts import render, redirect
|
||||
import pandas as pd
|
||||
from django.core.files.storage import FileSystemStorage
|
||||
import pickle, os
|
||||
from sklearn.preprocessing import OneHotEncoder
|
||||
from sklearn.impute import SimpleImputer
|
||||
import numpy as np
|
||||
from . import utils
|
||||
|
||||
|
||||
fig = None
|
||||
excel_file_name_preprocessed = "dataset_preprocessed.csv"
|
||||
excel_file_name = "dataset.csv"
|
||||
|
||||
def home(request):
|
||||
global fig
|
||||
global excel_file_name
|
||||
global excel_file_name_preprocessed
|
||||
|
||||
if request.method == 'POST':
|
||||
excel_file = request.FILES["excel_file"]
|
||||
excel_file_name = request.FILES["excel_file"].name
|
||||
df = pd.read_csv(excel_file)
|
||||
|
||||
fs = FileSystemStorage() #defaults to MEDIA_ROOT
|
||||
request.session['excel_file_name'] = excel_file_name
|
||||
fs.save(excel_file_name, excel_file)
|
||||
|
||||
idx = excel_file_name.index('.')
|
||||
excel_file_name_preprocessed = excel_file_name[:idx] + "_preprocessed" + excel_file_name[idx:]
|
||||
fs = FileSystemStorage() #defaults to MEDIA_ROOT
|
||||
request.session['excel_file_name_preprocess'] = excel_file_name_preprocessed
|
||||
fs.save(excel_file_name_preprocessed, excel_file)
|
||||
|
||||
# if file for preprocessing does not exist create it
|
||||
if os.path.exists(excel_file_name_preprocessed) == False:
|
||||
df = pd.read_csv(excel_file_name)
|
||||
df.to_csv(excel_file_name_preprocessed)
|
||||
|
||||
# collect the data to render
|
||||
df = pd.read_csv(excel_file_name)
|
||||
data_to_display = df[:5].to_html()
|
||||
|
||||
request.session['data_to_display'] = data_to_display
|
||||
request.session['excel_file_name'] = excel_file_name
|
||||
request.session['excel_file_name_preprocessed'] = excel_file_name_preprocessed
|
||||
labels = df.columns
|
||||
|
||||
context = {'data_to_display': data_to_display, 'excel_file': excel_file_name, 'labels': labels, 'fig': fig}
|
||||
return render(request,'base/home.html', context)
|
||||
|
||||
def stats(request):
|
||||
global fig
|
||||
excel_file = request.session.get('excel_file_name')
|
||||
df = pd.read_csv(excel_file)
|
||||
import plotly.express as px
|
||||
if request.method == 'POST':
|
||||
feature1 = request.POST.get('feature1')
|
||||
feature2 = request.POST.get('feature2')
|
||||
else:
|
||||
feature1 = "MonthlyCharges"
|
||||
feature2 = "tenure"
|
||||
|
||||
fig = px.scatter(df, x=feature1, y=feature2, color='Churn')
|
||||
fig = fig.to_html(full_html=False)
|
||||
request.session['fig'] = fig
|
||||
return redirect('home')
|
||||
|
||||
def preprocess(request):
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
excel_file_name_preprocessed = request.session.get('excel_file_name_preprocessed')
|
||||
print(excel_file_name_preprocessed)
|
||||
data = pd.read_csv(excel_file_name_preprocessed)
|
||||
|
||||
if set(['No','customerID','Churn']).issubset(data.columns):
|
||||
data.drop(['No','customerID','Churn'],axis=1,inplace=True)
|
||||
|
||||
if request.method == 'POST':
|
||||
if 'std' in request.POST:
|
||||
# define standard scaler
|
||||
scaler = StandardScaler()
|
||||
# transform data
|
||||
num_d = data.select_dtypes(exclude=['object'])
|
||||
data[num_d.columns] = scaler.fit_transform(num_d)
|
||||
|
||||
if 'onehot' in request.POST:
|
||||
data = pd.get_dummies(data,columns=['gender', 'Partner', 'Dependents', 'PhoneService', 'MultipleLines',
|
||||
'InternetService', 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection',
|
||||
'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract',
|
||||
'PaperlessBilling', 'PaymentMethod'],drop_first = True)
|
||||
|
||||
if 'imp' in request.POST:
|
||||
data_numeric = data.select_dtypes(exclude=['object'])
|
||||
data_categorical = data.select_dtypes(exclude=['number'])
|
||||
imp = SimpleImputer(missing_values=np.nan, strategy='mean')
|
||||
data_numeric = pd.DataFrame(imp.fit_transform(data_numeric), columns = data_numeric.columns, index=data_numeric.index) #only apply imputer to numeric columns
|
||||
data = pd.concat([data_numeric, data_categorical], axis = 1)
|
||||
|
||||
os.remove(excel_file_name_preprocessed)
|
||||
data.to_csv(excel_file_name_preprocessed)
|
||||
return redirect('home')
|
||||
|
||||
def training(request):
|
||||
global fig
|
||||
excel_file = request.session.get('excel_file_name')
|
||||
data = pd.read_csv(excel_file)
|
||||
|
||||
y=data['Churn']
|
||||
y=y.replace({"Yes":1,"No":0})
|
||||
from sklearn.model_selection import train_test_split
|
||||
X_train, X_test, y_train, y_test = train_test_split(data, y, test_size=0.2, random_state=0)
|
||||
X_train.to_csv("X_train.csv")
|
||||
X_test.to_csv("X_test.csv")
|
||||
y_train.to_csv("y_train.csv")
|
||||
y_test.to_csv("y_test.csv")
|
||||
|
||||
if 'logit' in request.POST:
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
clf = LogisticRegression(random_state=0).fit(X_train, y_train)
|
||||
filename = 'lg.sav'
|
||||
pickle.dump(clf, open(filename, 'wb'))
|
||||
return redirect('home')
|
||||
|
||||
if 'xgb' in request.POST:
|
||||
from xgboost import XGBClassifier
|
||||
xgb = XGBClassifier(learning_rate = 0.01,n_estimators=1000).fit(X_train, y_train)
|
||||
file_name = 'xgb.sav'
|
||||
pickle.dump(xgb,open(file_name,'wb'))
|
||||
return render(request,'base/home.html', {})
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
BIN
lg.sav
BIN
lg.sav
Binary file not shown.
BIN
xgb.sav
BIN
xgb.sav
Binary file not shown.
1199
y_test.csv
1199
y_test.csv
File diff suppressed because it is too large
Load Diff
4789
y_train.csv
4789
y_train.csv
File diff suppressed because it is too large
Load Diff
Loading…
x
Reference in New Issue
Block a user