【*】AI Go Senior 补充 (2021)

环境安装

在使用Python开发AI时，由于需时时查看处理中的训练资料，于是大多使用Jupyter Notebook进行开发。这是利用Python是直译式程式语言的的特点，在这里就不说太多，到底要如何安装Jupyter Notebook呢？

Google Colab

优点：免下载、已预先安装大多数的函式库、搞不好速度比你家电脑快、档案会自动清除。
缺点：若想储存资料须将资料下载或将Colab挂接到Google Drive、说不定比你家电脑慢、不能长时间闲置（会停止运算，但档案还在）

使用

点开连结：Colab

首次登入介面：
(未登入Google)

嘿对~我Windows还没启用，但我其实有买，这就是另一个故事了～

(已登入Google)

一共有5+1个选项：

範例：打开预设的範例程式最近：可以快速存取最近的程式Google 云端硬碟：在Google Drive内打开（会自动存档）GitHub：複製GitHub上的专案上传：上传并打开本地的档案（通常Jupyter Notebook会以.ipynb作为副档名）。取消：在右下角，直接跳过这个步骤并使用预设的程式範例。（不会自动存档，视窗关掉就没了）

这里我们选择[取消]，如果要储存档案的话可以之后在左上方的[档案]中选择储存的位置。

如果觉得预设的範例很丑，可以点选第一个区块（我们称之为Cell），然后按垃圾桶进行删除。

经一阵猛点后：

接着可以新增一个[+程式码](Python)或[文字](MarkDown)

P.S：可以透过Cell右上方的箭头来调整Cell的顺序、
MarkDown的话可以点击[关闭Markdown编辑器](在设定旁边)来显示内容。

再来点及右上方共用底下有一个连线，点他来连线到主机后，点选程式码区块左边的执行储存格。
结果：

Google的Colab先到这边，剩下的未来遇到再说，也可以先自行探索喔～（例如使用GPU加速、Google特有的TPU等等）

Anaconda

如果不想执行在云端的话，另一个我推荐的是使用Anaconda IDE，他整合了许多资料科学套件，除了跑得有点慢，他会是你资料科学之旅的好朋友。

安装与建立环境

下载连结：Anaconda
能选64位元就选64位元，不然大量的数据灌下去你的电脑不知道要算到牛年马月。（当然这取决于作业系统及硬体配置，详细方法请见：如何查询你的Windows系统是32或64位元？）

安装完成后（就狂点下一步），初始画面如下：

接着点选Environments

当然，你的画面会没有"PyAI"这个虚拟环境，现在就来创一个吧～

点选[Create]
打上自己想要的名子，版本我是选3.8啦～

然后按[Create]
之后要选环境就可以进来这里选，或是在首页的地方有个"Applications on"可以切换。

接着安装未来会用到的函式库，保持在"Environments"，中间有个箭头"<"给他按下去。
有一个选单"Installed"选成"Not Installed"，再来右边可以搜寻，找到下面这几个package给他点选起来：

scikit-learnpandaskerasmatplotlibrequest

都选完后，右下方有个[Apply]，按下去。

确认过眼神后，再[Apply]一次。

除了透过GUI的套件管理来下载函式库外，也可以用终端机安装。
把箭头按回去后，点一下绿色三角形（记得要确认环境正确喔～不要到时候装错=.=）
点[Open Terminal]来使用pip进行安装。
来安装个套件看看：

Jupyter Notebook

OK，回到主页。往下滑找到Jupyter Notebook，并按下[Install]

安装完后可以打开。会从浏览器开在本地端的伺服器（其实也可以对外远端使用Jupyter）
初始画面：

找到/建立一个你喜欢的资料夹（我是放在桌面拉，会叫做Desktop）
进到该资料夹后，右上方有个[New]

选择Python就可以建立一个ipynb档拉～

机器学习

多元线性回归 Multiple Regression

from sklearn import datasets, linear_modelfrom sklearn.metrics import r2_scorefrom sklearn.model_selection import train_test_splitdiabetes = datasets.load_diabetes()diabetes_X = diabetes.datadiabetes_y = diabetes.targetdiabetes_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)}')

多项式回归 Polynomial Regression

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npfrom sklearn.preprocessing import PolynomialFeaturesfrom sklearn.pipeline import make_pipelinefrom sklearn.linear_model import LinearRegressionrng = 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)

岭回归 Ridge Regression

import numpy as npfrom sklearn import datasets, linear_modelfrom sklearn.metrics import r2_scorefrom sklearn.model_selection import train_test_splitdiabetes = datasets.load_diabetes()diabetes_X = diabetes.datadiabetes_y = diabetes.targetdiabetes_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, datasetsfrom sklearn.model_selection import train_test_splitfrom sklearn import preprocessingfrom sklearn.metrics import accuracy_scoreiris = datasets.load_iris()X = iris.datay = iris.targetmodel = 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))

决策树 Decision Tree

from sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.datasets import load_irisfrom sklearn.tree import DecisionTreeClassifierfrom sklearn import preprocessingiris = load_iris()X = iris.data y = iris.targetX_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))

随机森林 Random Forest

from sklearn.ensemble import RandomForestClassifierfrom sklearn import preprocessingfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.datasets import load_irisiris = load_iris()X = iris.data y = iris.targetX_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))

支援向量机 SVM

from sklearn.datasets import load_breast_cancerfrom sklearn import preprocessingfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn.svm import SVCcancer = load_breast_cancer()X = cancer.data y = cancer.targetX_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))

单纯贝式 Naive Bayes

from sklearn import datasetsfrom sklearn.naive_bayes import MultinomialNBfrom sklearn import preprocessingfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scoreiris = datasets.load_iris()X = iris.data y = iris.targetX_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))

深度学习

深度神经网路 DNN

import numpy as npfrom keras.models import Sequentialfrom keras.layers.core import Dense, Activationfrom 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 layermodel.add(Activation('relu')) #activation function from input layer to 1st hidden layermodel.add(Dense(units=3))model.add(Activation('relu')) #activation function from 1st hidden layer to 2end hidden layermodel.add(Dense(units=2)) #num of classes in output layermodel.add(Activation('softmax')) #activation function from 2end hidden layer to output layermodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])score = model.fit(data, target, epochs=100)

卷积神经网路 CNN

import numpy as npfrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Activation, Flatten  from keras.layers import Convolution2D, MaxPooling2D from keras.utils import np_utilsfrom 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]))

循环神经网路 RNN

==== 待更 ====