環境安裝

在使用Python開發AI時，由於需時時查看處理中的訓練資料，於是大多使用Jupyter Notebook進行開發。這是利用Python是直譯式程式語言的的特點，在這裡就不說太多，到底要如何安裝Jupyter Notebook呢？

Google Colab

優點：免下載、已預先安裝大多數的函式庫、搞不好速度比你家電腦快、檔案會自動清除。
缺點：若想儲存資料須將資料下載或將Colab掛接到Google Drive、說不定比你家電腦慢、不能長時間閒置（會停止運算，但檔案還在）

使用

點開連結：Colab

首次登入介面：
(未登入Google)

嘿對~我Windows還沒啟用，但我其實有買，這就是另一個故事了～

(已登入Google)

一共有5+1個選項：

• 範例：打開預設的範例程式
• 最近：可以快速存取最近的程式
• Google 雲端硬碟：在Google Drive內打開（會自動存檔）
• GitHub：複製GitHub上的專案
• 上傳：上傳並打開本地的檔案（通常Jupyter Notebook會以.ipynb作為副檔名）。
• 取消：在右下角，直接跳過這個步驟並使用預設的程式範例。（不會自動存檔，視窗關掉就沒了）

這裡我們選擇[取消]，如果要儲存檔案的話可以之後在左上方的[檔案]中選擇儲存的位置。

如果覺得預設的範例很醜，可以點選第一個區塊（我們稱之為Cell），然後按垃圾桶進行刪除。

經一陣猛點後：

接著可以新增一個[+程式碼](Python)或[文字](MarkDown)

P.S：可以透過Cell右上方的箭頭來調整Cell的順序、
MarkDown的話可以點擊[關閉Markdown編輯器](在設定旁邊)來顯示內容。

再來點及右上方共用底下有一個連線，點他來連線到主機後，點選程式碼區塊左邊的執行儲存格。
結果：

Google的Colab先到這邊，剩下的未來遇到再說，也可以先自行探索喔～（例如使用GPU加速、Google特有的TPU等等）

Anaconda

如果不想執行在雲端的話，另一個我推薦的是使用Anaconda IDE，他整合了許多資料科學套件，除了跑得有點慢，他會是你資料科學之旅的好朋友。

安裝與建立環境

下載連結：Anaconda
能選64位元就選64位元，不然大量的數據灌下去你的電腦不知道要算到牛年馬月。（當然這取決於作業系統及硬體配置，詳細方法請見：如何查詢你的Windows系統是32或64位元？）

安裝完成後（就狂點下一步），初始畫面如下：

接著點選Environments

當然，你的畫面會沒有"PyAI"這個虛擬環境，現在就來創一個吧～

點選[Create]
打上自己想要的名子，版本我是選3.8啦～

然後按[Create]
之後要選環境就可以進來這裡選，或是在首頁的地方有個"Applications on"可以切換。

接著安裝未來會用到的函式庫，保持在"Environments"，中間有個箭頭"<"給他按下去。
有一個選單"Installed"選成"Not Installed"，再來右邊可以搜尋，找到下面這幾個package給他點選起來：

• scikit-learn
• pandas
• keras
• matplotlib
• request

都選完後，右下方有個[Apply]，按下去。

確認過眼神後，再[Apply]一次。

除了透過GUI的套件管理來下載函式庫外，也可以用終端機安裝。
把箭頭按回去後，點一下綠色三角形（記得要確認環境正確喔～不要到時候裝錯=.=）
點[Open Terminal]來使用pip進行安裝。
來安裝個套件看看：

Jupyter Notebook

OK，回到主頁。往下滑找到Jupyter Notebook，並按下[Install]

安裝完後可以打開。會從瀏覽器開在本地端的伺服器（其實也可以對外遠端使用Jupyter）
初始畫面：

找到/建立一個你喜歡的資料夾（我是放在桌面拉，會叫做Desktop）
進到該資料夾後，右上方有個[New]

選擇Python就可以建立一個ipynb檔拉～

機器學習

多元線性回歸 Multiple Regression

from sklearn import datasets, linear_model
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split

diabetes = datasets.load_diabetes()

diabetes_X = diabetes.data
diabetes_y = diabetes.target

diabetes_X_train, diabetes_X_test, diabetes_y_train, diabetes_y_test = train_test_split(diabetes_X, diabetes_y, test_size=0.2)

model = linear_model.LinearRegression()

model.fit(diabetes_X_train, diabetes_y_train)

diabetes_y_pred = model.predict(diabetes_X_test)

print(f'R2 score: {r2_score(diabetes_y_test, diabetes_y_pred)}')

多項式回歸 Polynomial Regression

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LinearRegression

rng = np.random.RandomState(10)
x = 10 * rng.rand(30)
y = np.sin(x) + 0.1 * rng.randn(30)

poly_model = make_pipeline(PolynomialFeatures(7), LinearRegression())
poly_model.fit(x[:, np.newaxis], y)

xfit = np.linspace(0, 10, 100)
yfit = poly_model.predict(xfit[:, np.newaxis])

plt.scatter(x, y)
plt.plot(xfit, yfit)

嶺回歸 Ridge Regression

import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split

diabetes = datasets.load_diabetes()

diabetes_X = diabetes.data
diabetes_y = diabetes.target

diabetes_X_train, diabetes_X_test, diabetes_y_train, diabetes_y_test = train_test_split(diabetes_X, diabetes_y, test_size=0.2)

model = linear_model.Ridge(alpha=1.0)

model.fit(diabetes_X_train, diabetes_y_train)

diabetes_y_pred = model.predict(diabetes_X_test)


print(f'R2 score: {r2_score(diabetes_y_test, diabetes_y_pred)}')

K-NN

from sklearn import neighbors, datasets
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.metrics import accuracy_score

iris = datasets.load_iris()
X = iris.data
y = iris.target

model = neighbors.KNeighborsClassifier() 
model.fit(X, y)

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

scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)

model = neighbors.KNeighborsClassifier()
model.fit(X_train, y_train)


X_test = scaler.transform(X_test)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print('accuracy: {}'.format(accuracy))

決策樹 Decision Tree

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn import preprocessing

iris = load_iris()
X = iris.data 
y = iris.target

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

scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)

model = DecisionTreeClassifier()
model.fit(X_train, y_train)

X_test = scaler.transform(X_test)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print('accuracy: {}'.format(accuracy))

隨機森林 Random Forest

from sklearn.ensemble import RandomForestClassifier
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris

iris = load_iris()
X = iris.data 
y = iris.target

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

scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)

model = RandomForestClassifier(max_depth=6, n_estimators=10)
model.fit(X_train, y_train)

X_test = scaler.transform(X_test)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print('accuracy: {}'.format(accuracy))

支援向量機 SVM

from sklearn.datasets import load_breast_cancer
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC

cancer = load_breast_cancer()

X = cancer.data 
y = cancer.target

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

scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)

model = SVC(kernel='rbf')
model.fit(X_train, y_train)

X_test = scaler.transform(X_test)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print('accuracy: {}'.format(accuracy))

單純貝式 Naive Bayes

from sklearn import datasets
from sklearn.naive_bayes import MultinomialNB
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


iris = datasets.load_iris()

X = iris.data 
y = iris.target

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

scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)

model = MultinomialNB()
model.fit(X_train, y_train)

X_test = scaler.transform(X_test)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print('accuracy: {}'.format(accuracy))

深度學習

深度神經網路 DNN

import numpy as np

from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.utils import np_utils


#preparing data for Exclusive OR (XOR)

attributes = [
   #x1, x2
    [0, 0]
  , [0, 1]
  , [1, 0]
  , [1, 1]
]

labels = [
    [1, 0] 
  , [0, 1]
  , [0, 1]
  , [1, 0]
]

data = np.array(attributes, 'int64')
target = np.array(labels, 'int64')

model = Sequential()

model.add(Dense(units=3 , input_shape=(2,))) #num of features in input layer
model.add(Activation('relu')) #activation function from input layer to 1st hidden layer
model.add(Dense(units=3))
model.add(Activation('relu')) #activation function from 1st hidden layer to 2end hidden layer
model.add(Dense(units=2)) #num of classes in output layer
model.add(Activation('softmax')) #activation function from 2end hidden layer to output layer

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

score = model.fit(data, target, epochs=100)

卷積神經網路 CNN

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten  
from keras.layers import Convolution2D, MaxPooling2D 
from keras.utils import np_utils
from keras.datasets import mnist 

(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(X_train.shape[0],28, 28, 1) 
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)

Y_train = np_utils.to_categorical(y_train, 10) 
Y_test = np_utils.to_categorical(y_test, 10)

model = Sequential()

model.add(Convolution2D(32, (3, 3), activation='relu', input_shape=(28,28,1))) 
model.add(Convolution2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=32, epochs=1, verbose=1)

score = model.evaluate(X_test, Y_test)
print('Test accuracy: {}'.format(score[1]))

循環神經網路 RNN

==== 待更 ====