Kaggle Course：Intermediate Machine Learning

Drop missing values
Get names of columns with missing values:
cols_with_missing = [col for col in X_train.columns
if X_train[col].isnull().any()]

Drop columns in training and validation data:
reduced_X_train = X_train.drop(cols_with_missing, axis=1)
reduced_X_valid = X_valid.drop(cols_with_missing, axis=1)

**

sklearn.impute.SimpleImputer

**
class sklearn.impute.SimpleImputer(, missing_values=nan, strategy=‘mean’, fill_value=None, verbose=0, copy=True, add_indicator=False)*
sklearn.impute.SimpleImputer

Imputation
my_imputer = SimpleImputer()
imputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))
imputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))添加链接描述

Imputation removed column names; put them back
imputed_X_train.columns = X_train.columns
imputed_X_valid.columns = X_valid.columns

One-hot encoding
We use the OneHotEncoder class from scikit-learn to get one-hot encodings. There are a number of parameters that can be used to customize its behavior.

We set handle_unknown=‘ignore’ to avoid errors when the validation data contains classes that aren’t represented in the training data, and(我们设置* handle_unknown ='ignore’以避免在验证数据包含训练数据中未表示的类时出错，并且)
setting sparse=False ensures that the encoded columns are returned as a numpy array (instead of a sparse matrix).(设置 sparse = False *可确保将编码的列作为numpy数组（而不是稀疏矩阵）返回。)

1.根据数据类型选择特征 select_dtypes(include=[’’]/exclude=[])
链接1
LabelEncoder
Methods

fit(y) Fit label encoder

fit_transform(y) Fit label encoder and return encoded labels

get_params([deep]) Get parameters for this estimator.

inverse_transform(y) Transform labels back to original encoding.

**set_params(params) Set the parameters of this estimator.

transform(y) Transform labels to normalized encoding.

import pandas as pd
from sklearn.model_selection import train_test_split

# Read the data
X_full = pd.read_csv('../input/train.csv', index_col='Id')
X_test_full = pd.read_csv('../input/test.csv', index_col='Id')

# Remove rows with missing target, separate target from predictors
X_full.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = X_full.SalePrice
X_full.drop(['SalePrice'], axis=1, inplace=True)

# Break off validation set from training data
X_train_full, X_valid_full, y_train, y_valid = train_test_split(X_full, y, 
                                                                train_size=0.8, test_size=0.2,
                                                                random_state=0)

# "Cardinality" means the number of unique values in a column
# Select categorical columns with relatively low cardinality (convenient but arbitrary)
categorical_cols = [cname for cname in X_train_full.columns if
                    X_train_full[cname].nunique() < 10 and 
                    X_train_full[cname].dtype == "object"]

# Select numerical columns
numerical_cols = [cname for cname in X_train_full.columns if 
                X_train_full[cname].dtype in ['int64', 'float64']]

# Keep selected columns only
my_cols = categorical_cols + numerical_cols
X_train = X_train_full[my_cols].copy()
X_valid = X_valid_full[my_cols].copy()
X_test = X_test_full[my_cols].copy()
# Save test predictions to file
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error

# Preprocessing for numerical data
numerical_transformer = SimpleImputer(strategy='constant')

# Preprocessing for categorical data
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

# Bundle preprocessing for numerical and categorical data
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_cols),
        ('cat', categorical_transformer, categorical_cols)
    ])

# Define model
model = RandomForestRegressor(n_estimators=100, random_state=0)

# Bundle preprocessing and modeling code in a pipeline
clf = Pipeline(steps=[('preprocessor', preprocessor),
                      ('model', model)
                     ])

# Preprocessing of training data, fit model 
clf.fit(X_train, y_train)

# Preprocessing of validation data, get predictions
preds = clf.predict(X_valid)

print('MAE:', mean_absolute_error(y_valid, preds))


numerical_transformer = SimpleImputer(strategy='mean') # Your code here

# Preprocessing for categorical data # Your code here
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='constant')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])


# Bundle preprocessing for numerical and categorical data
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_cols),
        ('cat', categorical_transformer, categorical_cols)
    ])

# Define model
model = RandomForestRegressor(n_estimators=100, random_state=0) # Your code here

# Bundle preprocessing and modeling code in a pipeline
my_pipeline = Pipeline(steps=[('preprocessor', preprocessor),
                              ('model', model)
                             ])

# Preprocessing of training data, fit model 
my_pipeline.fit(X_train, y_train)

# Preprocessing of validation data, get predictions
preds = my_pipeline.predict(X_valid)

# Evaluate the model
score = mean_absolute_error(y_valid, preds)
print('MAE:', score)

# Bundle preprocessing and modeling code in a pipeline
my_pipeline = Pipeline(steps=[('preprocessor', preprocessor),
                              ('model', model)
                             ])

# Preprocessing of training data, fit model 
my_pipeline.fit(X_train, y_train)

# Preprocessing of validation data, get predictions
preds = my_pipeline.predict(X_valid)

# Evaluate the model
score = mean_absolute_error(y_valid, preds)
print('MAE:', score)

# Preprocessing of test data, fit model
preds_test = my_pipeline.predict(X_test) # Your code here

# Save test predictions to file
output = pd.DataFrame({'Id': X_test.index,
                       'SalePrice': preds_test})
output.to_csv('submission.csv', index=False)

import pandas as pd
from sklearn.model_selection import train_test_split

# Read the data
train_data = pd.read_csv('../input/train.csv', index_col='Id')
test_data = pd.read_csv('../input/test.csv', index_col='Id')

# Remove rows with missing target, separate target from predictors
train_data.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = train_data.SalePrice              
train_data.drop(['SalePrice'], axis=1, inplace=True)

# Select numeric columns only
numeric_cols = [cname for cname in train_data.columns if train_data[cname].dtype in ['int64', 'float64']]
X = train_data[numeric_cols].copy()
X_test = test_data[numeric_cols].copy()
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer

my_pipeline = Pipeline(steps=[
    ('preprocessor', SimpleImputer()),
    ('model', RandomForestRegressor(n_estimators=50, random_state=0))
])
from sklearn.model_selection import cross_val_score

# Multiply by -1 since sklearn calculates *negative* MAE
scores = -1 * cross_val_score(my_pipeline, X, y,
                              cv=5,
                              scoring='neg_mean_absolute_error')

print("Average MAE score:", scores.mean())

import pandas as pd
from sklearn.model_selection import train_test_split

# Read the data
X = pd.read_csv('../input/train.csv', index_col='Id')
X_test_full = pd.read_csv('../input/test.csv', index_col='Id')

# Remove rows with missing target, separate target from predictors
X.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = X.SalePrice              
X.drop(['SalePrice'], axis=1, inplace=True)

# Break off validation set from training data
X_train_full, X_valid_full, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2,
                                                                random_state=0)

# "Cardinality" means the number of unique values in a column
# Select categorical columns with relatively low cardinality (convenient but arbitrary)
low_cardinality_cols = [cname for cname in X_train_full.columns if X_train_full[cname].nunique() < 10 and 
                        X_train_full[cname].dtype == "object"]

# Select numeric columns
numeric_cols = [cname for cname in X_train_full.columns if X_train_full[cname].dtype in ['int64', 'float64']]

# Keep selected columns only
my_cols = low_cardinality_cols + numeric_cols
X_train = X_train_full[my_cols].copy()
X_valid = X_valid_full[my_cols].copy()
X_test = X_test_full[my_cols].copy()

# One-hot encode the data (to shorten the code, we use pandas)
X_train = pd.get_dummies(X_train)
X_valid = pd.get_dummies(X_valid)
X_test = pd.get_dummies(X_test)
X_train, X_valid = X_train.align(X_valid, join='left', axis=1)
X_train, X_test = X_train.align(X_test, join='left', axis=1)
from xgboost import XGBRegressor

# Define the model
my_model_1 = XGBRegressor(random_state=0) # Your code here

# Fit the model
my_model_1.fit(X_train,y_train) # Your code here
from sklearn.metrics import mean_absolute_error

# Get predictions
predictions_1 = my_model_1.predict(X_valid) # Your code here
# Calculate MAE
mae_1 = mean_absolute_error(predictions_1,y_valid) # Your code here

# Uncomment to print MAE
print("Mean Absolute Error:" , mae_1)