def BivariateMiniBatchTool(noBatches):
batchSize = len(trainInputs) // noBatches
regressor = linear_model.SGDRegressor(alpha=0.01,
max_iter=1000,
average=batchSize,
shuffle=False)
regressor.fit(trainInputs, trainOutputs)
w0, w1, w2 = regressor.intercept_[0], regressor.coef_[0], regressor.coef_[
1]
w = [w0, w1, w2]
print("-----with tool-----")
print("Regression for attributes: GDP & Freedom")
print("\tThe learnt model: f(X,w) = " + str(w0) + " + " + str(w1) +
" * X1 + " + str(w2) + " * X2")
computedTestOutputs = regressor.predict(testInputs)
print("\tPrediction error (tool): ",
str(mean_squared_error(testOutputs, computedTestOutputs)))
print("\tPrediction error (manual): ",
str(meanSquareError(testOutputs, computedTestOutputs)))
plotDataForBi(gdpData, freedomData, outputs, w, "Train & test data")
plotDataForBi(trainGdp, trainFreedom, trainOutputs, w,
"Train data and the learnt model")
plotData2ForBi(testGdp, testFreedom, testOutputs, computedTestOutputs,
"Computed(green) vs real(red) test data")
def UnivariateMiniBatchTool(noBatches):
batchSize = len(trainGdp) // noBatches
regressor = linear_model.SGDRegressor(alpha=0.01,
max_iter=1000,
average=batchSize,
shuffle=False)
xx = [[el] for el in trainGdp]
regressor.fit(xx, trainOutputs)
w0, w1 = regressor.intercept_[0], regressor.coef_[0]
w = [w0, w1]
print("-----with tool-----")
print("Regression for attribute: GDP")
print("\tThe learnt model: f(X,w) = " + str(w0) + " + " + str(w1) + " * X")
computedOutputs = regressor.predict([[x] for x in testGdp])
print("\tPrediction error (tool): ",
str(mean_squared_error(testOutputs, computedOutputs)))
print("\tPrediction error (manual): ",
str(meanSquareError(testOutputs, computedOutputs)))
plotDataForUni(gdpData, outputs, w, "Train & test data")
plotDataForUni(trainGdp, trainOutputs, w,
"Train data and the learnt model")
plotData2ForUni(testGdp, testOutputs, computedOutputs,
"Computed vs real test data")
def main():
currDir = os.getcwd()
path = os.path.join(currDir, '2017.csv')
input, output = readData(path, 'Economy..GDP.per.Capita.', 'Freedom',
'Happiness.Score')
# split in 80/20 percent
np.random.seed(5)
indexes = [i for i in range(len(input))]
trainSample = np.random.choice(indexes,
int(0.8 * len(input)),
replace=False)
testSample = [i for i in indexes if not i in trainSample]
trainInputs = [input[i] for i in trainSample]
trainOutputs = [output[i] for i in trainSample]
testInputs = [input[i] for i in testSample]
testOutputs = [output[i] for i in testSample]
print('=== SKLEARN MODEL ===')
tool_regressor = tool_regression(trainInputs, trainOutputs)
# print('Tool predict ' + str(tool_regressor.predict(testInputs)))
print('\n\n=== MY MODEL ===')
manual_regressor = manual_regression(trainInputs, trainOutputs)
# print('Manual predict ' + str(manual_regressor.predict(testInputs)))
print('\n\n===Performance===')
print('Tool prediction error: ',
mean_squared_error(testOutputs, tool_regressor.predict(testInputs)))
print('Manual prediction error: ',
meanSquareError(manual_regressor, testInputs, testOutputs))
plotDataHistogram([input[i][0] for i in range(0, len(trainInputs))],
'capita GDP')
plotDataHistogram([input[i][1] for i in range(0, len(trainInputs))],
'freedom')
plotDataHistogram(trainOutputs, 'Happiness score')
plotData([trainInputs[i][0] for i in range(0, len(trainInputs))],
[trainInputs[i][1] for i in range(0, len(trainOutputs))],
trainOutputs, [
manual_regressor.intercept_, manual_regressor.coef_[0],
manual_regressor.coef_[1]
], 'TRAIN BASED ON LEARNT MODEL')
plotData([testInputs[i][0] for i in range(0, len(testInputs))],
[testInputs[i][1] for i in range(0, len(testInputs))],
testOutputs, [
manual_regressor.intercept_, manual_regressor.coef_[0],
manual_regressor.coef_[1]
], 'TEST BASED ON LEARNT MODEL')
predictedPlot([testInputs[i][0] for i in range(0, len(testInputs))],
[testInputs[i][1]
for i in range(0, len(testInputs))], testOutputs,
manual_regressor.predict(testInputs),
'PREDICTED BASED ON LEARNT MODEL')
def BivariateStochastic():
regressor = MySGDRegression()
regressor.fit(trainInputs, trainOutputs)
w0, w1, w2 = regressor.intercept_, regressor.coef_[0], regressor.coef_[1]
w = [w0, w1, w2]
print("-----manual stochastic-----")
print("Regression for attributes: GDP & Freedom")
print("\tThe learnt model: f(X,w) = " + str(w0) + " + " + str(w1) +
" * X1 + " + str(w2) + " * X2")
computedTestOutputs = regressor.predict(testInputs)
print("\tPrediction error (tool): ",
str(mean_squared_error(testOutputs, computedTestOutputs)))
print("\tPrediction error (manual): ",
str(meanSquareError(testOutputs, computedTestOutputs)))
plotDataForBi(gdpData, freedomData, outputs, w, "Train & test data")
plotDataForBi(trainGdp, trainFreedom, trainOutputs, w,
"Train data and the learnt model")
plotData2ForBi(testGdp, testFreedom, testOutputs, computedTestOutputs,
"Computed(green) vs real(red) test data")
def UnivariateStochastic():
regressor = MySGDRegression()
xx = [[el] for el in trainGdp]
regressor.fit(xx, trainOutputs)
w0, w1 = regressor.intercept_, regressor.coef_[0]
w = [w0, w1]
print("-----manual stochastic-----")
print("Regression for attribute: GDP")
print("\tThe learnt model: f(X,w) = " + str(w0) + " + " + str(w1) + " * X")
computedOutputs = regressor.predict([[x] for x in testGdp])
print("\tPrediction error (tool): ",
str(mean_squared_error(testOutputs, computedOutputs)))
print("\tPrediction error (manual): ",
str(meanSquareError(testOutputs, computedOutputs)))
plotDataForUni(gdpData, outputs, w, "Train & test data")
plotDataForUni(trainGdp, trainOutputs, w,
"Train data and the learnt model")
plotData2ForUni(testGdp, testOutputs, computedOutputs,
"Computed vs real test data")
# manual
regressor2 = MyLinearBivariateRegression()
regressor2.fit(trainInputs, trainOutputs)
wPrim = [regressor2.intercept_, regressor2.coef_[0], regressor2.coef_[1]]
print("-----manual-----")
print("The learnt model: f(X,w) = " + str(wPrim[0]) + " + " +
str(wPrim[1]) + " * X1 + " + str(wPrim[2]) + " * X2")
# print("Real: " + str(testOutputs))
# print("Computed: " + str(list(regressor2.predict(testInputs))))
print("-----performance-----")
print("Prediction error (tool): ",
str(mean_squared_error(testOutputs, regressor2.predict(testInputs))))
print("Prediction error (manual): ",
str(meanSquareError(testOutputs, regressor2.predict(testInputs))))
plotDataHistogram(gdpData, 'GDP')
plotDataHistogram(freedomData, 'Freedom')
plotDataHistogram(outputs, 'Happiness score')
# for train and test data
plotData(gdpData, freedomData, outputs, w, "Train & test data")
# for train data
plotData(trainGdp, trainFreedom, trainOutputs, w,
"Train data and the learnt model")
# for test data
computedTestOutputs = regressor2.predict(testInputs)
plotData2(testGdp, testFreedom, testOutputs, computedTestOutputs,
def main():
currDir = os.getcwd()
path = os.path.join(currDir, 'data.csv')
input, output = readData(path, 'Economy..GDP.per.Capita.', 'Freedom',
'Happiness.Score')
# split in 80/20 percent
np.random.seed(5)
indexes = [i for i in range(len(input))]
trainSample = np.random.choice(indexes,
int(0.8 * len(input)),
replace=False)
testSample = [i for i in indexes if not i in trainSample]
trainInputs = [input[i] for i in trainSample]
trainOutputs = [output[i] for i in trainSample]
testInputs = [input[i] for i in testSample]
testOutputs = [output[i] for i in testSample]
#data normalization
trainInputs, testInputs, trainOutputs, testOutputs = executeNormalization(
trainInputs, testInputs, trainOutputs, testOutputs)
#tool univariate
GDPTrainInputs = [trainInputs[0] for _ in range(len(trainInputs))]
GDPTestInputs = [testInputs[0] for _ in range(len(testInputs))]
print(" UNIVARIATE")
print("SKLEARN REGRESSION")
regressorSklearnUni = linear_model.SGDRegressor(alpha=0.005,
max_iter=1000,
average=len(trainInputs))
regressorSklearnUni.fit(GDPTrainInputs, trainOutputs)
w = [regressorSklearnUni.intercept_[0], regressorSklearnUni.coef_[0]]
print("Learnt model is: f(x) = " + str(w[0]) + " + " + str(w[1]) + " * x")
print("MANUAL REGRESSION")
regressorMySGDRegression = MySGDRegression()
regressorMySGDRegression.fit(GDPTrainInputs, trainOutputs)
w = [
regressorMySGDRegression.intercept_, regressorMySGDRegression.coef_[0]
]
print("Learnt model is: f(x) = " + str(w[0]) + " + " + str(w[1]) + " * x")
print("\n\n BIVARIATE")
print("SKLEARN REGRESSION")
toolRegression = tool_regression(trainInputs, trainOutputs)
print("MANUAL REGRESSION")
manual_regressor = manual_regression(trainInputs, trainOutputs)
print("\n\n ERRORS")
print(
"1.TOOL UNIVARIATE ERROR: ",
mean_squared_error(testOutputs, toolRegression.predict(GDPTestInputs)))
print("2.MANUAL UNIVARIATE ERROR: ",
meanSquareError(manual_regressor, GDPTestInputs, testOutputs))
print("3.TOOL BIVARIATE ERROR: ",
mean_squared_error(testOutputs, toolRegression.predict(testInputs)))
print("4.MANUAL BIVARIATE ERROR: ",
meanSquareError(manual_regressor, testInputs, testOutputs))
