def predict(self, this_dict):
first_variable_value = this_dict[self.first_variable]
for key in self.df.columns:
if key not in (self.first_variable, self.dependent_variable):
exponent = float(key.split('^')[1])
value = first_variable_value**exponent
this_dict[key] = value
linear_regressor = LinearRegressor(self.df, self.dependent_variable)
return linear_regressor.predict(this_dict)
print('Does all the linear_regressor stuff work')
reg_coeff = regressor.coefficients.copy()
for (key, value) in reg_coeff.items():
reg_coeff[key] = round(value, 8)
assert reg_coeff == {
'constant': 0.19252336,
'scoops of chocolate': -0.05981308,
'scoops of vanilla': 0.13271028
}, 'No, coefficients does not work'
assert round(
regressor.predict({
'scoops of chocolate': 2,
'scoops of vanilla': 3
}), 8) == 0.47102804, 'No, predict does not work'
print('Yes they do', "\n")
df = DataFrame.from_array(
[[0, 0, 1], [1, 0, 2], [2, 0, 4], [4, 0, 8], [6, 0, 9], [0, 2, 2],
[0, 4, 5], [0, 6, 7], [0, 8, 6], [2, 2, 0], [3, 4, 0]],
columns=['beef', 'pb', 'rating'])
df = df.create_interaction_terms('beef', 'pb')
assert df.columns == ['beef', 'pb', 'rating', 'beef * pb']
assert df.to_array() == [[0, 0, 1, 0], [1, 0, 2, 0], [2, 0, 4,
0], [4, 0, 8, 0],
[6, 0, 9, 0], [0, 2, 2, 0], [0, 4, 5,
import sys
sys.path.append('src')
from matrix import Matrix
from dataframe import DataFrame
from linear_regressor import LinearRegressor
df = DataFrame.from_array(
[[0, 0, 1], [1, 0, 2], [2, 0, 4], [4, 0, 8], [6, 0, 9], [0, 2, 2],
[0, 4, 5], [0, 6, 7], [0, 8, 6]],
columns=['slices of roast beef', 'tbsp of peanut butter', 'rating'])
regressor = LinearRegressor(df, dependent_variable='rating')
print(regressor.coefficients)
print(
regressor.predict({
'slices of roast beef': 5,
'tbsp of peanut butter': 0
}))
print(
regressor.predict({
'slices of roast beef': 5,
'tbsp of peanut butter': 5
}))
sys.path.append('src')
from linear_regressor import LinearRegressor
from logistic_regressor import LogisticRegressor
from matrix import Matrix
from dataframe import DataFrame
df = DataFrame.from_array(
[[0, 0, 1], [1, 0, 2], [2, 0, 4], [4, 0, 8], [6, 0, 9], [0, 2, 2],
[0, 4, 5], [0, 6, 7], [0, 8, 6]],
columns=['slices of roast beef', 'tablespoons of peanut butter', 'rating'])
regressor = LinearRegressor(df, dependent_variable='rating')
print(regressor.coefficients)
print(
regressor.predict({
'slices of roast beef': 5,
'tablespoons of peanut butter': 0
}))
print(
regressor.predict({
'slices of roast beef': 5,
'tablespoons of peanut butter': 5
}))
df = DataFrame.from_array(
[[0, 0, 1], [1, 0, 2], [2, 0, 4], [4, 0, 8], [6, 0, 9], [0, 2, 2],
[0, 4, 5], [0, 6, 7], [0, 8, 6], [2, 2, 0], [3, 4, 0]],
columns=['beef', 'pb', 'rating'])
df = df.create_interaction_terms('beef', 'pb')
} == {
'constant': 0.19252336,
'scoops of chocolate': -0.05981308,
'scoops of vanilla': 0.13271028
}, {
key: round(regressor.coefficients[key], 7)
for key in regressor.coefficients
}
print('PASSED')
# these coefficients are rounded, you should only round
# in your assert statement
print('Testing method predict...')
assert round(
regressor.predict({
'scoops of chocolate': 2,
'scoops of vanilla': 3
}), 8) == 0.47102804
print('PASSED')
df = DataFrame.from_array(
[[0, 0, [], 1], [0, 0, ['mayo'], 1], [0, 0, ['jelly'], 4],
[0, 0, ['mayo', 'jelly'], 0], [5, 0, [], 4], [5, 0, ['mayo'], 8],
[5, 0, ['jelly'], 1], [5, 0, ['mayo', 'jelly'], 0], [0, 5, [], 5],
[0, 5, ['mayo'], 0], [0, 5, ['jelly'], 9], [0, 5, ['mayo', 'jelly'], 0],
[5, 5, [], 0], [5, 5, ['mayo'], 0], [5, 5, ['jelly'], 0],
[5, 5, ['mayo', 'jelly'], 0]],
columns=['beef', 'pb', 'condiments', 'rating'])
df = df.create_dummy_variables('condiments')
df = df.create_interaction_terms('beef', 'pb')
'rating': [1, 1, 4, 0, 4, 8, 1, 0, 5, 0, 9, 0, 0, 0, 0, 0]
})
linear_regressor = LinearRegressor(df, prediction_column = 'rating')
print("\n Testing Coefficients of LinearRegressor")
assert linear_regressor.coefficients == {'beef': 0.25, 'pb': 0.4, 'mayo': -1.25, 'jelly': 1.5, 'beef_pb': -0.21, 'beef_mayo': 1.05, 'beef_jelly': -0.85, 'pb_mayo': -0.65, 'pb_jelly': 0.65, 'mayo_jelly': -3.25, 'constant': 2.19}, 'Incorrect coefficients for Linear Regressor'
print(" passed")
print("\n Testing Gathering all inputs of LinearRegressor")
assert linear_regressor.gather_all_inputs({ 'beef': 5, 'pb': 5, 'mayo': 1, 'jelly': 1}) == {'beef': 5, 'pb': 5, 'mayo': 1, 'jelly': 1, 'beef_pb': 25, 'beef_mayo': 5, 'beef_jelly': 5, 'pb_mayo': 5, 'pb_jelly': 5, 'mayo_jelly': 1, 'constant': 1}, 'Incorrect gather_all_inputs'
print(" passed")
print("\n Testing Prediction #1")
assert linear_regressor.predict({'beef': 5, 'pb': 5, 'mayo': 1, 'jelly': 1}) == -1.81, 'Incorrect prediction from linear regressor'
print(" passed")
print("\n Testing Prediction #2")
assert linear_regressor.predict({
'beef': 0,
'pb': 3,
'mayo': 0,
'jelly': 1,
}) == 6.84 , 'Incorrect prediction from linear regressor'
print(" passed")
print("\n Testing Prediction #3")
assert linear_regressor.predict({
'beef': 1,
'pb': 1,
'mayo': 1,
'jelly': 0,
'mayo': [1],
'jelly': [1],
'beef_pb': [25],
'beef_mayo': [5],
'beef_jelly': [5],
'pb_mayo': [5],
'pb_jelly': [5],
'mayo_jelly': [1],
'constant': [1]
}
assert linear_regressor.current_input.data_dict == input_dict, 'Wrong INputs'
assert linear_regressor.predict({
'beef': 5,
'pb': 5,
'mayo': 1,
'jelly': 1,
}) == -1.8125, 'Nah'
assert linear_regressor.predict({
'beef': 0,
'pb': 3,
'mayo': 0,
'jelly': 1,
}) == 6.8375, 'Nah'
assert linear_regressor.predict({
'beef': 1,
'pb': 1,
'mayo': 1,
'jelly': 0,
new_df = DataFrame(new_dict, new_columns)
training_df = new_df.select_rows([i for i in range(501)])
testing_df = new_df.select_rows(
[i for i in range(501, len(new_df.to_array()))])
print('\nSex:')
sex_df = training_df.select(['Sex', 'Survived'])
test_sex_df = testing_df.select(['Sex', 'Survived'])
survival_regressor = LinearRegressor(sex_df, 'Survived')
print(survival_regressor.coefficients)
correct_classifications = 0
for i in range(len(training_df.data_dict['Sex'])):
prediction = round(
survival_regressor.predict(
{var: sex_df.data_dict[var][i]
for var in sex_df.columns[:-1]}))
if prediction > 1:
prediction = 1
if prediction == sex_df.data_dict['Survived'][i]:
correct_classifications += 1
print('train accuracy:',
correct_classifications / len(training_df.data_dict['Sex']))
correct_classifications = 0
for i in range(len(testing_df.data_dict['Sex'])):
prediction = round(
survival_regressor.predict({
var: test_sex_df.data_dict[var][i]
for var in test_sex_df.columns[:-1]