Machine Learning Specialization笔记（2）- Machine Learning Foundations: A Case Study Approach（上）

 # 导入turicreate库

    
 import turicreate
    
  
    
 # 基于people-example.csv创建SFrame对象
    
 sf = turicreate.SFrame('people-example.csv')
    
  
    
 # 查看表格
    
 sf # 查看前几行
    
 sf.tail() # 查看后几行

 # 显示所有列的数据

    
 sf.show()

 # sf['target_column'].show()

    
 sf['age'].show()

 # 求某列的平均值

    
 sf['age'].mean()
    
  
    
 # 求某列的最大/最小值
    
 sf['age'].max()
    
 sf['age'].min()
    
  
    
 # 新建列并赋值
    
 sf['Full Name'] = sf['First Name'] + ' ' + sf['Last Name']

 # 定义函数：transform_country，把所有的USA转换成United States

    
 def transform_country(country):
    
     if country == 'USA':
    
     return 'United States'
    
     else:
    
     return country
    
  
    
 # 对每一列都进行transform_country函数操作
    
 sf['Country'] = sf['Country'].apply(transform_country)
    
  
    
 # 展示效果
    
 sf

 import turicreate

    
  
    
 sf = turicreate.SFrame('people_wiki.sframe/')
    
  
    
 sf

 num_rows = sf.num_rows()

    
 print(num_rows)

 last_row = sf[-1]

    
 name_in_last_row = last_row['name']
    
 print(name_in_last_row)

 # Filter the SFrame for rows where the name column is 'Harpdog Brown'

    
 harpdog_brown_row = sf[sf['name'] == 'Harpdog Brown']
    
  
    
 # Access the text column in the filtered SFrame
    
 if harpdog_brown_row:
    
     harpdog_brown_text = harpdog_brown_row['text'][0]  # Assuming 'text' is the column name
    
     print(harpdog_brown_text)
    
 else:
    
     print("Harpdog Brown not found in the SFrame")

 # Sort the SFrame by the 'text' column in ascending order

    
 sorted_sf = sf.sort('text')
    
  
    
 # Get the name from the first row of the sorted SFrame
    
 first_name = sorted_sf['name'][0]
    
 print(first_name)

 import turicreate

    
  
    
 sales = turicreate.SFrame('home_data.sframe/')

    turicreate.show(sales[1:5000]['sqft_living'],sales[1:5000]['price'])

 # .8：设置80%为训练集的比例

    
 training_set, test_set = sales.random_split(.8,seed=0)

 # 用sqft_living解释price

    
 sqft_model = turicreate.linear_regression.create(training_set,target='price',features=['sqft_living'])

 # max_error: 预测值与实际值之间的最大误差

    
 # rmse: 均方根误差
    
 print (sqft_model.evaluate(test_set))

    sqft_model.coefficients

 import matplotlib.pyplot as plt

    
 %matplotlib inline
    
 plt.plot(test_set['sqft_living'],test_set['price'],'.',
    
     test_set['sqft_living'],sqft_model.predict(test_set),'-')

 # 多个变量

    
 my_features = ['bedrooms','bathrooms','sqft_living','sqft_lot','floors','zipcode']
    
  
    
 # 建立模型
    
 my_features_model = turicreate.linear_regression.create(training_set,target='price',features=my_features)
    
  
    
 # 评估模型
    
 print (my_features_model.evaluate(test_set))
    
  
    
 # 预测房价
    
 house1 = sales[sales['id']=='5309101200']
    
 print (my_features_model.predict(house1))

 import turicreate as tc

    
  
    
 sales = tc.SFrame('home_data.sframe/')
    
  
    
 # 按邮编分组，并计算平均房价
    
 average_prices_by_zip = sales.groupby('zipcode', {'avg_price': tc.aggregate.MEAN('price')})
    
  
    
 # 按平均房价排序，找到最高
    
 highest_avg_price_zip = average_prices_by_zip.sort('avg_price', ascending=False)[0]
    
  
    
 # 输出结果
    
 print(highest_avg_price_zip)

 # 过滤面积在 2000 和 4000范围内的房子

    
 houses_in_range = sales[(sales['sqft_living'] >= 2000) & (sales['sqft_living'] <= 4000)]
    
  
    
 # 计算比例
    
 fraction = len(houses_in_range) / len(sales)
    
  
    
 print(fraction)

 training_set, test_set = sales.random_split(.8,seed=0)

    
  
    
 # 定义特征集
    
 my_features = ['bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'zipcode']
    
 advanced_features = [
    
 'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'zipcode',
    
 'condition', # condition of house
    
 'grade', # measure of quality of construction
    
 'waterfront', # waterfront property
    
 'view', # type of view
    
 'sqft_above', # square feet above ground
    
 'sqft_basement', # square feet in basement
    
 'yr_built', # the year built
    
 'yr_renovated', # the year renovated
    
 'lat', 'long', # the lat-long of the parcel
    
 'sqft_living15', # average sq.ft. of 15 nearest neighbors 
    
 'sqft_lot15', # average lot size of 15 nearest neighbors 
    
 ]
    
  
    
 # 训练my_features_model
    
 my_features_model = tc.linear_regression.create(training_set, target='price', features=my_features)
    
  
    
 # 训练advanced_features_model
    
 advanced_features_model = tc.linear_regression.create(training_set, target='price', features=advanced_features)
    
  
    
 # 评估模型
    
 my_features_evaluation = my_features_model.evaluate(test_set)
    
 advanced_features_evaluation = advanced_features_model.evaluate(test_set)
    
  
    
 # 计算RMSE差值
    
 rmse_difference = my_features_evaluation['rmse'] - advanced_features_evaluation['rmse']