Projekt_Si/decisiontree.py

import pandas as pd 
import matplotlib.pyplot as plt 
from sklearn.model_selection import train_test_split
import category_encoders as ce
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
import random
import graphviz
import warnings
warnings.filterwarnings('ignore')

data = './database/datasetadult.csv'
df = pd.read_csv(data)
#print(df.shape)
#print(df.head())
#print(df.info())
#print(df['Outfit'].value_counts())
#print(df.isnull().sum())

X = df.drop(['Adult'], axis=1)

y = df['Adult']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33, random_state = 42)
#print(X_train.shape, X_test.shape)
#print(X_train.dtypes)
#print(X_train.head())

encoder = ce.OrdinalEncoder(cols=['Wrinkles', 'Balding', 'Beard', 'Outfit', 'Glasses', 'Tattoo', 'Hair', 'Behaviour'])

X_train = encoder.fit_transform(X_train)

X_test = encoder.transform(X_test)

#print(X_train.head())
#print(X_test.head())
clf_en = DecisionTreeClassifier(criterion='entropy', max_depth=200, random_state=0)
clf_en.fit(X_train, y_train)

y_pred_en = clf_en.predict(X_test)
#print('Model accuracy score with criterion entropy: {0:0.4f}'.format(accuracy_score(y_test, y_pred_en)))

y_pred_train_en = clf_en.predict(X_train)
#print('Training-set accuracy score: {0:0.4f}'.format(accuracy_score(y_train, y_pred_train_en)))

#print('Training set score: {:.4f}'.format(clf_en.score(X_train, y_train)))
#print('Test set score: {:.4f}'.format(clf_en.score(X_test, y_test)))

#nowy klient testowo
"""new_client = {
    "Wrinkles": random.choice(['Yes', 'No']),
    "Balding": random.choice(['Yes', 'No']),
    "Beard": random.choice(['Yes', 'No']),
    "Outfit": random.choice(['Messy', 'Casual','Formal']),
    "Glasses": random.choice(['Yes', 'No']),
    "Tattoo": random.choice(['Yes', 'No']),
    "Hair": random.choice(['Color', 'Grey', 'Natural']),
    "Behaviour": random.choice(['Energetic', 'Stressed', 'Calm'])
} """

def predict_client(client_data,glasses):
    new_client = {
    "Wrinkles": client_data.zmarszczki,
    "Balding": client_data.lysienie,
    "Beard": client_data.broda,
    "Outfit": client_data.ubior,
    "Glasses": 'Yes' if glasses == 1 else 'No',
    "Tattoo": client_data.tatuaz,
    "Hair": client_data.wlosy,
    "Behaviour": client_data.zachowanie
    }
    new_client_df = pd.DataFrame(new_client, index=[0])
    new_client_df_encoded = encoder.transform(new_client_df)
    prediction = clf_en.predict(new_client_df_encoded)
    print('Model accuracy score with criterion entropy: {0:0.4f}'.format(accuracy_score(y_test, y_pred_en)))
    print('Training-set accuracy score: {0:0.4f}'.format(accuracy_score(y_train, y_pred_train_en)))

    print('Training set score: {:.4f}'.format(clf_en.score(X_train, y_train)))
    print('Test set score: {:.4f}'.format(clf_en.score(X_test, y_test)))
    
    dot_data = tree.export_graphviz(clf_en, out_file=None, 
                              feature_names=X_train.columns,  
                              class_names=y_train.unique(),  
                              filled=True, rounded=True,  
                              special_characters=True)
    
    graph = graphviz.Source(dot_data) 
    graph.render("decision_tree", format='png')

    return prediction[0]

#print("\nNew client:")
#print(new_client_df)
#print("Prediction:", prediction[0])