Sklearn

Kaggle ML Course

Reading and looking at the shape of the data

import pandas as pd

melbourne_file_path = '../input/melbourne-housing-snapshot/melb_data.csv'
melbourne_data = pd.read_csv(melbourne_file_path) 
melbourne_data.columns
# The Melbourne data has some missing values (some houses for which some variables weren't recorded.)
# We'll learn to handle missing values in a later tutorial.  
# Your Iowa data doesn't have missing values in the columns you use. 
# So we will take the simplest option for now, and drop houses from our data. 
# Don't worry about this much for now, though the code is:

# dropna drops missing values (think of na as "not available")
melbourne_data = melbourne_data.dropna(axis=0)
# Seleting the target prediction
y = melbourne_data.Price
# Choosing features to help you predict the target
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'Lattitude', 'Longtitude']
# Concention is that the data is called X
X = melbourne_data[melbourne_features]
X.describe()
X.head()

Define the Model

from sklearn.tree import DecisionTreeRegressor

# Define model. Specify a number for random_state to ensure same results each run
melbourne_model = DecisionTreeRegressor(random_state=1)

# Fit model
melbourne_model.fit(X, y)
print("Making predictions for the following 5 houses:")
print(X.head())
print("The predictions are")
print(melbourne_model.predict(X.head()))

Mean Absolute Error

from sklearn.metrics import mean_absolute_error

predicted_home_prices = melbourne_model.predict(X)
mean_absolute_error(y, predicted_home_prices)

Split data into test and validation sets

from sklearn.model_selection import train_test_split

# split data into training and validation data, for both features and target
# The split is based on a random number generator. Supplying a numeric value to
# the random_state argument guarantees we get the same split every time we
# run this script.
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state = 0)
# Define model
melbourne_model = DecisionTreeRegressor()
# Fit model
melbourne_model.fit(train_X, train_y)

# get predicted prices on validation data
val_predictions = melbourne_model.predict(val_X)
print(mean_absolute_error(val_y, val_predictions))

Be careful and consider the effects of both over/underfitting

# Code you have previously used to load data
import pandas as pd
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor


# Path of the file to read
iowa_file_path = '../input/home-data-for-ml-course/train.csv'

home_data = pd.read_csv(iowa_file_path)
# Create target object and call it y
y = home_data.SalePrice
# Create X
features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']
X = home_data[features]

# Split into validation and training data
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=1)

# Specify Model
iowa_model = DecisionTreeRegressor(random_state=1)
# Fit Model
iowa_model.fit(train_X, train_y)

# Make validation predictions and calculate mean absolute error
val_predictions = iowa_model.predict(val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE: {:,.0f}".format(val_mae))

# Set up code checking
from learntools.core import binder
binder.bind(globals())
from learntools.machine_learning.ex5 import *
print("\nSetup complete")

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)

# Here is a short solution with a dict comprehension.
# The lesson gives an example of how to do this with an explicit loop.
scores = {leaf_size: get_mae(leaf_size, train_X, val_X, train_y, val_y) for leaf_size in candidate_max_leaf_nodes}
best_tree_size = min(scores, key=scores.get)

Fit Model Using All Data

# Fit the model with best_tree_size. Fill in argument to make optimal size
final_model = DecisionTreeRegressor(max_leaf_nodes=best_tree_size, random_state=1)

# fit the final model
final_model.fit(X, y)

• sklearn.metrics.mean_absolute_error
• sklearn.tree.DecisionTreeRegressor
  • https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeRegressor.html
• sklearn.ensemble.RandomForestRegressor

import pandas as pd

# Load data
melbourne_file_path = '../input/melbourne-housing-snapshot/melb_data.csv'
melbourne_data = pd.read_csv(melbourne_file_path) 
# Filter rows with missing values
melbourne_data = melbourne_data.dropna(axis=0)
# Choose target and features
y = melbourne_data.Price
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea', 
					  'YearBuilt', 'Lattitude', 'Longtitude']
X = melbourne_data[melbourne_features]

from sklearn.model_selection import train_test_split

# split data into training and validation data, for both features and target
# The split is based on a random number generator. Supplying a numeric value to
# the random_state argument guarantees we get the same split every time we
# run this script.
train_X, val_X, train_y, val_y = train_test_split(X, y,random_state = 0)

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)
melb_preds = forest_model.predict(val_X)
print(mean_absolute_error(val_y, melb_preds))

• sklearn.impute.SimpleImputer
  • Inserting the mean value of the column into the NA values so that it can lend itself to modeling purposes still without generating outliers or skewing the probability curve with anything other than the mean

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))

• Better yet than just imputing is to track which values were imputed by row/column reference so that you can see the model differences by including and excluding those values

# 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))

# Shape of training data (num_rows, num_columns)
print(X_train.shape)

# Number of missing values in each column of training data
missing_val_count_by_column = (X_train.isnull().sum())
print(missing_val_count_by_column[missing_val_count_by_column > 0])