Breast Cancer Classification Web App using Streamlit

Breast-Cancer-Classifier-Web-App-using-Streamlit/Breast_Cancer_Classifier.ipynb

@@ -0,0 +1,337 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### BREAST CANCER CLASSIFICATION"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#importing the dependencies\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "from sklearn import metrics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>mean_radius</th>\n",
+       "      <th>mean_texture</th>\n",
+       "      <th>mean_perimeter</th>\n",
+       "      <th>mean_area</th>\n",
+       "      <th>mean_smoothness</th>\n",
+       "      <th>diagnosis</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>17.99</td>\n",
+       "      <td>10.38</td>\n",
+       "      <td>122.80</td>\n",
+       "      <td>1001.0</td>\n",
+       "      <td>0.11840</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>20.57</td>\n",
+       "      <td>17.77</td>\n",
+       "      <td>132.90</td>\n",
+       "      <td>1326.0</td>\n",
+       "      <td>0.08474</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>19.69</td>\n",
+       "      <td>21.25</td>\n",
+       "      <td>130.00</td>\n",
+       "      <td>1203.0</td>\n",
+       "      <td>0.10960</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.42</td>\n",
+       "      <td>20.38</td>\n",
+       "      <td>77.58</td>\n",
+       "      <td>386.1</td>\n",
+       "      <td>0.14250</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>20.29</td>\n",
+       "      <td>14.34</td>\n",
+       "      <td>135.10</td>\n",
+       "      <td>1297.0</td>\n",
+       "      <td>0.10030</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   mean_radius  mean_texture  mean_perimeter  mean_area  mean_smoothness  \\\n",
+       "0        17.99         10.38          122.80     1001.0          0.11840   \n",
+       "1        20.57         17.77          132.90     1326.0          0.08474   \n",
+       "2        19.69         21.25          130.00     1203.0          0.10960   \n",
+       "3        11.42         20.38           77.58      386.1          0.14250   \n",
+       "4        20.29         14.34          135.10     1297.0          0.10030   \n",
+       "\n",
+       "   diagnosis  \n",
+       "0          0  \n",
+       "1          0  \n",
+       "2          0  \n",
+       "3          0  \n",
+       "4          0  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#importing the dataset\n",
+    "data = pd.read_csv('Breast_cancer_data.csv')\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(569, 6)"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "mean_radius        0\n",
+       "mean_texture       0\n",
+       "mean_perimeter     0\n",
+       "mean_area          0\n",
+       "mean_smoothness    0\n",
+       "diagnosis          0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = data.drop(['diagnosis'],axis=1)\n",
+    "Y = data['diagnosis']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.2,stratify=Y,random_state=101)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(569, 5) (455, 5) (114, 5)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(X.shape,X_train.shape,X_test.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ran_classifier = RandomForestClassifier()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier()"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ran_classifier.fit(X_train,Y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testing_data_prediction1 = ran_classifier.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "score1 = metrics.accuracy_score(Y_test,testing_data_prediction1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.9122807017543859"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "score1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "\n",
+    "filename = 'Breast_Cancer_Classifier.sav'\n",
+    "pickle.dump(ran_classifier,open(filename,'wb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "486e0d5a79acdbfffd563ee7a67a93a5017bd2a4f66495483a69f0245c8a4a6c"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Breast-Cancer-Classifier-Web-App-using-Streamlit/Breast_Cancer_Classifier_Web_App.py

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Feb  8 22:59:27 2023
+
+@author: HP
+"""
+
+import numpy as np
+import pickle
+import streamlit as st
+
+#load the model
+loaded_model = pickle.load(open("Breast_Cancer_Classifier.sav",'rb'))
+
+def breast_cancer_classifer(input_data):
+    # changing the input_data to numpy array
+    input_data_as_numpy_array = np.asarray(input_data)
+
+    # reshape the array as we are predicting for one instance
+    input_data_reshaped = input_data_as_numpy_array.reshape(1,-1)
+
+    prediction = loaded_model.predict(input_data_reshaped)
+    print(prediction)
+
+    if (prediction[0] == 0):
+      return 'This is a Benign Tumour(Non-Cancerous)'
+    else:
+      return 'This is a Malignent Tumour(Cancerous)'
+
+def main():
+
+    #giving a title
+    st.title('Breast Cancer Classifier Web App')
+
+    #getting input from the user
+    mean_radius = st.text_input("Mean Radius")
+    mean_texture = st.text_input("Mean Texture")
+    mean_perimeter = st.text_input("Mean Perimeter")
+    mean_area = st.text_input("Mean Area")
+    mean_smoothness = st.text_input("Mean Smoothness")
+
+    #code for prediction
+    diagnosis = ''
+
+    # getting the input data from the user
+    if st.button('Heart Disease Test Result : '):
+        diagnosis = breast_cancer_classifer([mean_radius,mean_texture,mean_perimeter,mean_area,mean_smoothness])
+
+    st.success(diagnosis)
+
+if __name__ == "__main__":
+    main()

Breast-Cancer-Classifier-Web-App-using-Streamlit/README.md

@@ -0,0 +1,55 @@
+# Breast-Cancer-Classifier
+This is a Breast Cancer Classifier using Machine Learning.
+
+![Type](https://img.shields.io/badge/Machine-Learning-red.svg)
+![IDE](https://img.shields.io/badge/IDE-JupyterNotebook-orange.svg)
+![Type](https://img.shields.io/badge/Type-Supervised-yellow.svg)
+![Status](https://img.shields.io/badge/Status-Completed-cherryred.svg)
+
+Link to the web app : 
+
+<a href="https://dvamsidhar2002-breast-c-breast-cancer-classifier-web-app-xdlnez.streamlit.app/">
+    <img src="https://img.shields.io/badge/Breast Cancer Classifier-0A0A0A?style=plastic&logo=HERE&logoColor=white" height=20></a>
+
+
+
+### There are two types of tumours detected in human body : 
+
+<div>
+<img align = 'right' src = "Benign tumour.png" alt="Benign tumour" height=230 width=200>
+<h2>BENIGN TUMOUR</h2>
+<ul>
+  <li>  Non - Cancerous
+  <li>  Capsulated
+  <li>  Non - invasive
+  <li>  Slow growing
+  <li>  Do not spread to other parts of the body
+  <li>  Cells are normal
+</ul>
+</div>
+<br><hr>
+<div>
+<img align = 'right' src = "Malignant Tumour.png" alt="Malignant tumour" height=230 width=200>
+<h2>MALIGNANT TUMOUR</h2>
+<ul>
+  <li> Cancerous
+  <li> Non-Capsulated
+  <li> Invasive
+  <li> Fast growing
+  <li> Spread to other parts of the body
+  <li> Cells are abnormal
+</ul>
+</div>
+
+<h2 align="center">WORKFLOW OF THE PROJECT </h2>
+
+```mermaid
+flowchart TD
+
+A[Step 0 : Collect Data] --> B[Step 1 : Import Libraries/Modules in the workspace]
+B[Step 1 : Import Libraries/Modules in the workspace] --> C[Step 2 : Import the collected data into the workspace]
+C[Step 2 : Import the collected data into the workspace] --> D[Step 3 : Data Preprocessing]
+D[Step 3 : Data Preprocessing] --> E[Step 4 : Perform EDA by visualizing the data]
+E[Step 4 : Perform EDA by visualizing the data] --> F[Step 5 : Train ML model using LOGISTIC REGRESSION]
+F[Step 5 : Train ML model using LOGISTIC REGRESSION] --> G[Step 6 : Deploy ML model as a Web App]
+```

Breast-Cancer-Classifier-Web-App-using-Streamlit/requirements.txt

@@ -0,0 +1,4 @@
+numpy==1.21.4
+pickle-mixin==1.0.2
+streamlit==1.2.0
+scikit-learn==1.0.1