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)

print("MAE from Approach 1 (Drop columns with missing values):")
print(score_dataset(reduced_X_train, reduced_X_valid, y_train, y_valid))

2 - missing values : drop columns

4 - make prédiction

2 - missing values : Extension to Imputation

# Make copy to avoid changing original data (when imputing)
X_train_plus = X_train.copy()
X_valid_plus = X_valid.copy()

# Make new columns indicating what will be imputed
for col in cols_with_missing:
    X_train_plus[col + '_was_missing'] = X_train_plus[col].isnull()
    X_valid_plus[col + '_was_missing'] = X_valid_plus[col].isnull()

# Imputation
my_imputer = SimpleImputer()
imputed_X_train_plus = pd.DataFrame(my_imputer.fit_transform(X_train_plus))
imputed_X_valid_plus = pd.DataFrame(my_imputer.transform(X_valid_plus))

# Imputation removed column names; put them back
imputed_X_train_plus.columns = X_train_plus.columns
imputed_X_valid_plus.columns = X_valid_plus.columns

print("MAE from Approach 3 (An Extension to Imputation):")
print(score_dataset(imputed_X_train_plus, imputed_X_valid_plus, y_train, y_valid))

from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_absolute_error

melbourne_model = DecisionTreeRegressor(random_state=1)

melbourne_model.fit(X, y)





model_predictions = melbourne_model.predict(val_X)
print(mean_absolute_error(val_y, model_predictions))

3 - select model DecisionTreeRegressor

2 - categorical variables : label encoder

from sklearn.preprocessing import LabelEncoder

# Make copy to avoid changing original data 
label_X_train = X_train.copy()
label_X_valid = X_valid.copy()

# Apply label encoder to each column with categorical data
label_encoder = LabelEncoder()
for col in object_cols:
    label_X_train[col] = label_encoder.fit_transform(X_train[col])
    label_X_valid[col] = label_encoder.transform(X_valid[col])

print("MAE from Approach 2 (Label Encoding):") 
print(score_dataset(label_X_train, label_X_valid, y_train, y_valid))

from sklearn.metrics import mean_absolute_error

# predicted_values must be the result of a prediction
mean_absolute_error(y, predicted_values)

5 - evaluate model

drop_X_train = X_train.select_dtypes(exclude=['object'])
drop_X_valid = X_valid.select_dtypes(exclude=['object'])

print("MAE from Approach 1 (Drop categorical variables):")
print(score_dataset(drop_X_train, drop_X_valid, y_train, y_valid))

2 - categorical variables : drop values

3 - categorical variables : one hot encoding

# Using pipeline
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

# 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)
    ])


# Doing this manualy


from sklearn.preprocessing import OneHotEncoder

# Apply one-hot encoder to each column with categorical data
OH_encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)
OH_cols_train = pd.DataFrame(OH_encoder.fit_transform(X_train[object_cols]))
OH_cols_valid = pd.DataFrame(OH_encoder.transform(X_valid[object_cols]))

# One-hot encoding removed index; put it back
OH_cols_train.index = X_train.index
OH_cols_valid.index = X_valid.index

# Remove categorical columns (will replace with one-hot encoding)
num_X_train = X_train.drop(object_cols, axis=1)
num_X_valid = X_valid.drop(object_cols, axis=1)

# Add one-hot encoded columns to numerical features
OH_X_train = pd.concat([num_X_train, OH_cols_train], axis=1)
OH_X_valid = pd.concat([num_X_valid, OH_cols_valid], axis=1)

print("MAE from Approach 3 (One-Hot Encoding):") 
print(score_dataset(OH_X_train, OH_X_valid, y_train, y_valid))

plt.plot([x_0, x_1], [y_0, y_1], c='r')

# Label the graph axes.
plt.ylabel("median_house_value")
plt.xlabel("total_rooms")

# Plot a scatter plot from our data sample.
plt.scatter(sample["total_rooms"], sample["median_house_value"])

# Display graph.
plt.show()

2 - Visualize data

y = home_data.Price

home_features = ['Rooms', 'Bathroom', 'Landsize', 'Lattitude', 'Longtitude']
X = home_data[home_features]

# X.describe()
# X.head()

2 - define y and X

from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error

forest_model = RandomForestRegressor(random_state=1)
forest_model.fit(train_X, train_y)
model_predictions = forest_model.predict(val_X)
print(mean_absolute_error(val_y, model_predictions))

3 - select model RandomForestRegressor

# Using pipeline
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

# 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)
    ])


# Doing imputation manualy

from sklearn.impute import 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))

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

print("MAE from Approach 2 (Imputation):")
print(score_dataset(imputed_X_train, imputed_X_valid, y_train, y_valid))

2 - missing values : Imputation

file_path = '../input/home_data.csv'

home_data = pd.read_csv(file_path) 

# display data
home_data.describe()
home_data.columns

1 - Get the data

from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeRegressor

def get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y):
    model = DecisionTreeRegressor(max_leaf_nodes=max_leaf_nodes, random_state=0)
    model.fit(train_X, train_y)
    preds_val = model.predict(val_X)
    mae = mean_absolute_error(val_y, preds_val)
    return(mae)






for max_leaf_nodes in [5, 50, 500, 5000]:
    my_mae = get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y)
    print("Max leaf nodes: %d  \t\t MAE:  %d" %(max_leaf_nodes, my_mae))

ML