分类目录归档：机器学习
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('../datasets/Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
from sklearn.model_selection import train_test_split
X_tr...
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
from sklearn.model_selection import train_test_split
X_tr...
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
from sklearn.model_selection import train_test_split
X_train, ...
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
from sklearn.model_selection import train_test...
该数据集包含了社交网络中用户的信息。这些信息涉及用户ID,性别,年龄以及预估薪资。一家汽车公司刚刚推出了他们新型的豪华SUV，我们尝试预测哪些用户会购买这种全新SUV。并且在最后一列用来表示用户是否购买。我们将建立一种模型来预测用户是否购买这种SUV，该模型基于两个变量，分别是年龄和预计薪资。因此我们的特征矩阵将是这两列。我们尝试寻找用户年龄与预估薪资之间的某种相关性，以及他是否购买SUV的决定。
import numpy as np
import matplotlib.pyplot as plt
import pan...
import pandas as pd
import numpy as np
dataset = pd.read_csv('50_Startups.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[ : , 4 ].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder = LabelEncoder()
X[: , ...
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dataset = pd.read_csv('studentscores.csv')
X = dataset.iloc[ : , : 1 ].values
Y = dataset.iloc[ : , 1 ].values
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y...
如图所示，通过6步完成数据预处理。
import numpy as np
import pandas as pd
dataset = pd.read_csv('Data.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[ : , 3].values
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = "NaN"...