DecisionTree.py

import streamlit as st
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler,LabelEncoder
from sklearn.metrics import confusion_matrix,classification_report,ConfusionMatrixDisplay
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import LabelEncoder
from sklearn.tree import plot_tree

file = 'KFC.xlsx'
sheet = 'Clean_data'
df = pd.read_excel(file, sheet_name=sheet)

st.header('Decision Tree Classification')
st.write('Prediction Budget Type')

le = LabelEncoder()

df['orderType_enc']   = le.fit_transform(df['orderType'].astype(str))
df['occupation_enc']   = le.fit_transform(df['occupation'].astype(str))

df_x = df[["orderType_enc","age_enc","occupation_enc"]]
df_y = df[[ "budget"]]

feature_list = df_x.columns
class_list = df_y [ "budget"].unique()

scaler       = StandardScaler()
df_x_scaled  = scaler.fit_transform(df_x)

#Showing Count and Target Class Count
st.subheader('Count')
st.metric(label="Total Count", value = len(df_y),)
class_list = df_y [ "budget"].dropna().unique()
for cls in class_list:
    st.metric(label=cls,value=len(df_y[df_y[ "budget"]==cls]),)
    

#Number Input for Test Ratio

test_ratio = st.number_input("Select Ratio for Test Set", value = 0.2,)

#Setting The Test/Train Ratio
x_train, x_test, y_train, y_test = train_test_split(
    df_x_scaled, df_y, test_size = test_ratio,random_state = 3,
)

tree = DecisionTreeClassifier(max_depth=3)
tree.fit (x_train, y_train)

#Predict and evaluate
y_pred = tree.predict(x_test)

#Predict and evaluate
y_pred = tree.predict(x_test)
st.write(f"Test Accuracy:{accuracy_score(y_test,y_pred):.2f}")

#Drawing Decision Tree
plt.clf()
plt.figure(figsize=(20,20))
plot_tree(tree, filled = True, feature_names = df_x.columns, class_names=df_y["budget"].unique())
st.pyplot(plt)


#Setup Input for Prediiction of Unknown Record

occupation_enc = st.selectbox(
    "Occupation",
    options=[0, 1, 2, 3],
    format_func=lambda x: {
        0: 'Others',
        1: 'Staff',
        2: 'Student',
        3: 'TA'
    }[x]
)

orderType_enc = st.selectbox(
    "Order Type",
    options=[0, 1, 2, 3],
    format_func=lambda x: {
        0: 'group',
        1: 'individual',
        2: 'promotion',
        3: 'snack_sharing'
    }[x]
)

age_enc =st.selectbox(
    "Age",
    options=[1, 2, 3, 4, 5],
    format_func=lambda x: {
        1: 'under 18',
        2: '18-22',
        3: '23-27',
        4: '28-35',
        5: 'above 35'
    }[x]
)

#Predicting Class from Input
predict_data = pd.DataFrame({"Occupation":[occupation_enc],"Order Type":[orderType_enc],"Age":[age_enc]})
val = tree.predict(predict_data[["Occupation","Order Type","Age"]])[0]
accuracy = accuracy_score(y_test, y_pred)
st.write("Predicted Value:",val)
st.write("Test Accuracy",accuracy)