Merge pull request larymak#229 from SANJAY-NT/main

Add ML project script for Mushrooms Prediction

Author: larymak

MachineLearning Projects/Poisonous_Mushroom-project/README.md

@@ -0,0 +1,7 @@
+# ML_Mushroom-project
+A ML based Web App to show the SVM,Regression flow and distribution on poisonous mushroom Data set .
+Welcome to this hands-on project on building your first machine learning web app with the Streamlit library in Python. By the end of this project, you are going to be comfortable with using Python and Streamlit to build beautiful and interactive ML web apps with zero web development experience! We are going to load, explore, visualize and interact with data, and generate dashboards in less than 100 lines of Python code! Our web application will allows users to choose what classification algorithm they want to use and let them interactively set hyper-parameter values, all without them knowing to code!
+
+Prior experience with writing simple Python scripts and using pandas for data manipulation is recommended. It is required that you have an understanding of Logistic Regression, Support Vector Machines, and Random Forest Classifiers and how to use them in scikit-learn.
+
+

MachineLearning Projects/Poisonous_Mushroom-project/Script/app.py

@@ -0,0 +1,121 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.svm import SVC
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import plot_confusion_matrix, plot_roc_curve, plot_precision_recall_curve
+from sklearn.metrics import precision_score, recall_score
+
+def main():
+    st.title("Binary Classification Web App")
+    st.sidebar.title("Binary Classification Web App")
+    st.markdown("Are your mushrooms edible or poisonous? 🍄")
+    st.sidebar.markdown("Are your mushrooms edible or poisonous? 🍄")
+
+    @st.cache(persist=True)
+    def load_data():
+        data = pd.read_csv("C:\Users\SANJAY N T\Desktop\project\streamlit-ml\mushrooms.csv")
+        labelencoder=LabelEncoder()
+        for col in data.columns:
+            data[col] = labelencoder.fit_transform(data[col])
+        return data
+
+    @st.cache(persist=True)
+    def split(df):
+        y = df.type
+        x = df.drop(columns=['type'])
+        x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0)
+        return x_train, x_test, y_train, y_test
+
+    def plot_metrics(metrics_list):
+        if 'Confusion Matrix' in metrics_list:
+            st.subheader("Confusion Matrix")
+            plot_confusion_matrix(model, x_test, y_test, display_labels=class_names)
+            st.pyplot()
+
+        if 'ROC Curve' in metrics_list:
+            st.subheader("ROC Curve")
+            plot_roc_curve(model, x_test, y_test)
+            st.pyplot()
+
+        if 'Precision-Recall Curve' in metrics_list:
+            st.subheader('Precision-Recall Curve')
+            plot_precision_recall_curve(model, x_test, y_test)
+            st.pyplot()
+
+    df = load_data()
+    class_names = ['edible', 'poisonous']
+
+    x_train, x_test, y_train, y_test = split(df)
+
+    st.sidebar.subheader("Choose Classifier")
+    classifier = st.sidebar.selectbox("Classifier", ("Support Vector Machine (SVM)", "Logistic Regression", "Random Forest"))
+
+    if classifier == 'Support Vector Machine (SVM)':
+        st.sidebar.subheader("Model Hyperparameters")
+        #choose parameters
+        C = st.sidebar.number_input("C (Regularization parameter)", 0.01, 10.0, step=0.01, key='C_SVM')
+        kernel = st.sidebar.radio("Kernel", ("rbf", "linear"), key='kernel')
+        gamma = st.sidebar.radio("Gamma (Kernel Coefficient)", ("scale", "auto"), key='gamma')
+
+        metrics = st.sidebar.multiselect("What metrics to plot?", ('Confusion Matrix', 'ROC Curve', 'Precision-Recall Curve'))
+
+        if st.sidebar.button("Classify", key='classify'):
+            st.subheader("Support Vector Machine (SVM) Results")
+            model = SVC(C=C, kernel=kernel, gamma=gamma)
+            model.fit(x_train, y_train)
+            accuracy = model.score(x_test, y_test)
+            y_pred = model.predict(x_test)
+            st.write("Accuracy: ", accuracy.round(2))
+            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
+            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
+            plot_metrics(metrics)
+
+    if classifier == 'Logistic Regression':
+        st.sidebar.subheader("Model Hyperparameters")
+        C = st.sidebar.number_input("C (Regularization parameter)", 0.01, 10.0, step=0.01, key='C_LR')
+        max_iter = st.sidebar.slider("Maximum number of iterations", 100, 500, key='max_iter')
+
+        metrics = st.sidebar.multiselect("What metrics to plot?", ('Confusion Matrix', 'ROC Curve', 'Precision-Recall Curve'))
+
+        if st.sidebar.button("Classify", key='classify'):
+            st.subheader("Logistic Regression Results")
+            model = LogisticRegression(C=C, penalty='l2', max_iter=max_iter)
+            model.fit(x_train, y_train)
+            accuracy = model.score(x_test, y_test)
+            y_pred = model.predict(x_test)
+            st.write("Accuracy: ", accuracy.round(2))
+            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
+            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
+            plot_metrics(metrics)
+
+    if classifier == 'Random Forest':
+        st.sidebar.subheader("Model Hyperparameters")
+        n_estimators = st.sidebar.number_input("The number of trees in the forest", 100, 5000, step=10, key='n_estimators')
+        max_depth = st.sidebar.number_input("The maximum depth of the tree", 1, 20, step=1, key='n_estimators')
+        bootstrap = st.sidebar.radio("Bootstrap samples when building trees", ('True', 'False'), key='bootstrap')
+        metrics = st.sidebar.multiselect("What metrics to plot?", ('Confusion Matrix', 'ROC Curve', 'Precision-Recall Curve'))
+
+        if st.sidebar.button("Classify", key='classify'):
+            st.subheader("Random Forest Results")
+            model = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, bootstrap=bootstrap, n_jobs=-1)
+            model.fit(x_train, y_train)
+            accuracy = model.score(x_test, y_test)
+            y_pred = model.predict(x_test)
+            st.write("Accuracy: ", accuracy.round(2))
+            st.write("Precision: ", precision_score(y_test, y_pred, labels=class_names).round(2))
+            st.write("Recall: ", recall_score(y_test, y_pred, labels=class_names).round(2))
+            plot_metrics(metrics)
+
+    if st.sidebar.checkbox("Show raw data", False):
+        st.subheader("Mushroom Data Set (Classification)")
+        st.write(df)
+        st.markdown("This [data set](https://archive.ics.uci.edu/ml/datasets/Mushroom) includes descriptions of hypothetical samples corresponding to 23 species of gilled mushrooms "
+        "in the Agaricus and Lepiota Family (pp. 500-525). Each species is identified as definitely edible, definitely poisonous, "
+        "or of unknown edibility and not recommended. This latter class was combined with the poisonous one.")
+
+if __name__ == '__main__':
+    main()