securetorobert’s gists

securetorobert / regularization_imports.py

Last active July 12, 2018 00:45

Required imports for regularization tutorials

	#imports
	import numpy as np
	import pandas as pd
	import math

	from sklearn.model_selection import train_test_split

	from sklearn.linear_model import LinearRegression
	from sklearn.linear_model import Ridge
	from sklearn.linear_model import Lasso

securetorobert / train_test_split_boston.py

Created July 12, 2018 00:43

Train-test-split of Boston housing data

	#create our X and y
	X = train_df.drop('medv', axis=1)
	y = train_df['medv']

	X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42, test_size=0.3)

securetorobert / linear_regression_boston.py

Created July 12, 2018 00:47

Linear Regression Model for Boston housing data

	lr_model = LinearRegression()
	lr_model.fit(X_train, y_train)

	print('Training score: {}'.format(lr_model.score(X_train, y_train)))
	print('Test score: {}'.format(lr_model.score(X_test, y_test)))

	y_pred = lr_model.predict(X_test)
	mse = mean_squared_error(y_test, y_pred)
	rmse = math.sqrt(mse)

securetorobert / poly_features_lin_reg_boston.py

Created July 12, 2018 00:56

Create polynomial features on a linear regression model for Boston housing data

	steps = [
	('scalar', StandardScaler()),
	('poly', PolynomialFeatures(degree=2)),
	('model', LinearRegression())
	]

	pipeline = Pipeline(steps)

	pipeline.fit(X_train, y_train)

securetorobert / poly_features_ridge_boston.py

Created July 12, 2018 01:04

Polynomial features and ridge regression model applied to Boston housing data

	steps = [
	('scalar', StandardScaler()),
	('poly', PolynomialFeatures(degree=2)),
	('model', Ridge(alpha=10, fit_intercept=True))
	]

	ridge_pipe = Pipeline(steps)
	ridge_pipe.fit(X_train, y_train)

	print('Training Score: {}'.format(ridge_pipe.score(X_train, y_train)))

securetorobert / poly_features_lasso_boston.py

Created July 12, 2018 01:11

Polynomial features with lasso regression on Boston housing data

	steps = [
	('scalar', StandardScaler()),
	('poly', PolynomialFeatures(degree=2)),
	('model', Lasso(alpha=0.3, fit_intercept=True))
	]

	lasso_pipe = Pipeline(steps)

	lasso_pipe.fit(X_train, y_train)

securetorobert / loss_optimization_scipy.py

Created July 12, 2018 23:04

Loss optimization in scientific python

	import pandas as pd
	import numpy as np
	from scipy.optimize import fmin, minimize

	#load training data
	train_df = pd.read_csv('./train.csv', index_col='ID')
	y = train_df['medv'].values
	y = y.reshape(-1, 1)
	train_df['constant'] = 1
	columns = ['constant', 'crim', 'zn', 'indus', 'chas', 'nox', 'rm', 'age', 'dis', 'rad', 'tax', 'ptratio', 'black', 'lstat']

securetorobert / tf_estimator_linear_regressor.py

Created July 12, 2018 23:17

Linear Regression with TensorFlow canned estimators

	import numpy as np
	import pandas as pd
	import tensorflow as tf
	from sklearn.model_selection import train_test_split

	train_df = pd.read_csv('./train.csv')

	#create feature columns
	crim = tf.feature_column.numeric_column('crim', dtype=tf.float64, shape=())
	zn = tf.feature_column.numeric_column('zn', dtype=tf.float64, shape=())

securetorobert / loss_optimizer_tf.py

Created July 12, 2018 23:25

Optimizing loss functions in TensorFlow

	import pandas as pd
	import numpy as np
	import tensorflow as tf
	from tensorflow.python.ops import confusion_matrix
	from tensorflow.python.ops import math_ops

	train_df = pd.read_csv('./train.csv', index_col='ID')

	y = train_df['medv'].values
	y = y.reshape(-1, 1)

securetorobert / neural_network_boston_data_imports.py

Created July 12, 2018 23:43

Neural Network with Keras on Boston Housing data

	import pandas as pd
	from sklearn.preprocessing import MinMaxScaler
	import tensorflow as tf

	#read in training data
	train_df = pd.read_csv('train.csv', index_col='ID')
	train_df.head()

	target = 'medv'

Robert John securetorobert