[first song] Introduction to data science of rebirth -- return to advanced level

The first 1 Turn off ： Simple linear regression

Task description

Our mission ： Write a gradient descent applet , Output loss function .

Programming requirements

Please read the code on the right , Combined with relevant knowledge , stay Begin-End Code supplement within the area , Output for 1-10 Loss function value after sub gradient descent .

#********** Begin **********#
#  Gradient descent function ： take None Replace with the code you wrote 
def gradient_descent(x_i, y_i, w, b, alpha):
    dw =-2 * error(w, b, x_i, y_i)* x_i
    db =-2 * error(w, b, x_i, y_i)
    w =w - alpha * dw
    b = b - alpha * db
    return w, b
#********** End **********#


# read data
data_path ='task1/train.csv'
data = pd.read_csv(data_path)
# select property
data = data[['GrLivArea', 'SalePrice']]
# separate train and test data
train = data[:1168]
test = data[1168:]

# a fixed alpha slows down learning; here we use 10 iterations to show the error is decreasing\n",
x = test['GrLivArea'].tolist()
y = test['SalePrice'].tolist()
num_iterations = 10
alpha = 0.0000001
random.seed(0)
w, b = [random.random(), 0]

#********** Begin **********#
#  The gradient drops and outputs the value of the loss function ： take None Replace with the code you wrote 
for i in range(num_iterations):
    for x_i, y_i in zip(x, y):
        w, b = gradient_descent(x_i, y_i, w, b, alpha)
    print(sum_of_squared_errors(w, b, x, y))
#********** End **********#    

The first 2 Turn off ： Multiple linear regression

Task description

Our mission ： Write a small program to solve the multivariate linear model , And output the results of training set and test set RMSE value .

Programming requirements

Please read the code on the right , Combined with relevant knowledge , stay Begin-End Code supplement within the area , Output training set and test set RMSE value .

#********** Begin **********# The penalty weight is set to 30
#  Output training set prediction error ： Replacement and completion None Part of 
clf = Ridge(alpha=30)
clf.fit(x,y)
y_pred = clf.predict(x)
print(math.sqrt(mean_squared_error(y, y_pred)))
#********** End **********#

The first 3 Turn off ： Neural network regression

Task description

Our mission ： Use Keras Build a regression model .

Programming requirements

Please read the code on the right , Combined with relevant knowledge , stay Begin-End Code supplement within the area , Use Keras Build a regression model .SalePrice Is the target variable .

    # filter data
    predictors = data.select_dtypes(exclude=['object'])
    cols_with_no_nans = []
    for col in predictors.columns:
        if not data[col].isnull().any():
            cols_with_no_nans.append(col)

    data_filtered = data[cols_with_no_nans]
    data = data_filtered[['MSSubClass', 'LotArea', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', '1stFlrSF', '2ndFlrSF', 'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'TotRmsAbvGrd', 'Fireplaces', 'GarageCars', 'GarageArea', 'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal', 'MoSold', 'YrSold', 'SalePrice']]
    
    # separate train and test
    train = data[:1168]
    test = data[1168:]
    y = train[['SalePrice']]
    x = train[['MSSubClass', 'LotArea', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', '1stFlrSF', '2ndFlrSF', 'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'TotRmsAbvGrd', 'Fireplaces', 'GarageCars', 'GarageArea', 'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal', 'MoSold', 'YrSold']]

    # define model
    NN_model = Sequential()# Define a neural network model 
    
    #********* Begin *********#
    #  Mark all None Fill in and replace the part of 
    # input layer
    #  add to input layer, Use 128 Neurons , Initialize... In a normal way , Set the regular item to l2（ A weight 0.1）, Enter the dimension according to x According to the dimension of , use relu As an activation function 
    NN_model.add(Dense(128,# Fully connected layer 
    kernel_initializer='normal',# Initialize the weight 
    kernel_regularizer=l2(0.1),# Set regular items 
    input_dim = x.shape[1],# Define the input dimension 
    activation='relu'))# Set activation function 
    
    # hidden layers
    #  Add two layer, Every layer Use 256 Neurons , Initialize... In a normal way , Set the regular item to l2（ A weight 0.1）, use relu As an activation function 
    NN_model.add(Dense(256, kernel_initializer='normal', kernel_regularizer=l2(0.1), activation='relu'))
    NN_model.add(Dense(256, kernel_initializer='normal', kernel_regularizer=l2(0.1), activation='relu'))
    
    # output layer
    #  Add output layer, Use a neuron , use linear Activation function 
    NN_model.add(Dense(1, kernel_initializer='normal',activation='linear'))
    
    # compile and train network
    NN_model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mean_squared_error'])# Use adaptive learning rate adam
    NN_model.fit(x, y, epochs=500, batch_size=32, validation_split = 0.2,verbose=0)# Training times 、 Batch size 、 Verification and training set division ratio 
    
    # evaluate on test set
    test_x = test[['MSSubClass', 'LotArea', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', '1stFlrSF', '2ndFlrSF', 'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'TotRmsAbvGrd', 'Fireplaces', 'GarageCars', 'GarageArea', 'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal', 'MoSold', 'YrSold']]
    test_y = test[['SalePrice']]    
    
    test_y_pred = NN_model.predict(test_x)
    # return test error
    test_error = math.sqrt(mean_squared_error(test_y, test_y_pred))
    return test_error
    #********* End *********#
    

notes ： The content is only for reference and sharing , Do not spread without permission , Tort made delete