Lab work Decision Tree.ipynb

Kernel: Python 3 (ipykernel)

Participant Lab Notebook

Decision Tree Classification Lab

Follow the instructions step-by-step and complete all code sections.

#import Libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.metrics import accuracy_score, classification_report
import pickle

df = pd.read_csv("bodytype.csv")
df.head()

# TODO: Complete the EDA tasks:
# - df.shape
# - df.describe()
# - df.isna().sum()
# - Histograms
# - Scatter plot Height vs Weight coloured by BodyType

# Split Data into test and Train 

((80, 4), (20, 4))

# Baseline Decision Tree

#Evaluation and Prediction

## Grid Search

##Grid Search
params = {
    "max_depth": [2, 3, 4, 5],
    "min_samples_split": [2, 4, 6],
    "criterion": ["gini", "entropy"]
}

gs = GridSearchCV(DecisionTreeClassifier(), params, cv=5, n_jobs=-1)
gs.fit(X_train, y_train)
gs.best_params_

## Save Model

##Predict on New Sample data set
sample = pd.DataFrame([{
    "HeightCm":165,
    "WeightKg":70,
    "Age":30,
    "ActivityLevelEncoded":1
}])

model.predict(sample)