# 機器學習暫時程式碼
###### tags: `Study`

:::spoiler

from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier(criterion = 'entropy',random_state=0)
classifier.fit(x_test,y_test)

:::

這邊之後可以再用confusion_matrix來觀察

---

:::spoiler Decision Tree

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics

data = pd.read_csv('car_evaluation.csv')

data.columns

data['Class_Values'].value_counts()

data['Class_Values'].value_counts().plot(kind = 'bar')
plt.show()

data['safety'].value_counts().plot(kind = 'bar')
plt.show()

import seaborn as sns
sns.countplot(data['buying'], hue = data['Class_Values'])
plt.show()

data.info()

X = data.drop(['Class_Values'], axis = 1)
y = data['Class_Values']

from sklearn.preprocessing import OrdinalEncoder
buying_price_category = ['low', 'med', 'high', 'vhigh']
maint_cost_category = ['low', 'med', 'high', 'vhigh']
doors_category = ['2', '3', '4', '5more']
person_capacity_category = ['2', '4', 'more']
lug_boot_category = ['small', 'med', 'big']
safety_category = ['low', 'med', 'high']
all_categories = [buying_price_category, maint_cost_category,doors_category,person_capacity_category,lug_boot_category,safety_category]
oe = OrdinalEncoder(categories= all_categories)
X = oe.fit_transform( data[['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety']])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=0)

DT_classifier = DecisionTreeClassifier(criterion= 'entropy', random_state=0, max_depth= 3, min_samples_split= 10)
DT_classifier.fit(X_train, y_train)

y_pred = DT_classifier.predict(X_test)

confusion_matrix(y_test, y_pred)

from sklearn import tree
fig = plt.figure(figsize=(15,12))
_ = tree.plot(DT_classifier,feature_names=data.columns[:-1], class_names=DT_classifier.classes_, filled=True)

:::

:::spoiler K-means

# K-Means Clustering

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Mall_Customers.csv')
X = dataset.iloc[:, 3:5].values

# Using the elbow method to find the optimal number of clusters
from sklearn.cluster import KMeans
wcss = []
for i in range(1,11):
    kmeans = KMeans(n_clusters = i, max_iter = 300, n_init = 10, init = 'k-means++', random_state = 0)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)
plt.plot(range(1,11), wcss)
plt.title('The Elbow Method')
plt.xlabel('Number of Clusters')
plt.ylabel('WCSS')
plt.show()

# Applying the k-means to the mall dataset
kmeans = KMeans(n_clusters = 5, max_iter = 300, n_init = 10, init = 'k-means++', random_state = 0)
y_kmeans = kmeans.fit_predict(X)

# Visualizing the clusters
plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = 'red', label = 'Careful')
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Standard')
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Target')
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Careless')
plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Sensible')
plt.scatter(kmeans.cluster_centers_[:, 0],  kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')
plt.title('Clusters of clients')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()

:::