import numpy as np
from liblinear.liblinearutil import *
import math

FILENAME = "hw4_train.dat"

def read_data(filename):
    with open(filename) as fp:
        lines = fp.readlines()
        x, y = [], []
        for line in lines:
            numbers = [ float(i) for i in line.split() ]
            x.append(numbers[:-1])
            y.append(int(numbers[-1]))
    return x, y

def format(features):
    '''
        change to LIBSVM format
    '''
    results = []
    for feature in features:
        result = {}
        for index, value in enumerate(feature):
            if value != 0.0:
                result[index+1] = value
        results.append(result)
    return results
    
def error(gt, pred):
    err = 0
    for index in range(len(gt)):
        err = (err+1) if gt[index]!=pred[index] else err
    return err/len(gt)

x, y = read_data(FILENAME)
x = format(x)
prob = problem(y, x)
lambda_powers = [-6, -4, -2, 0, 2]

results = []
for lambda_power in lambda_powers:
    lambda_value = 10 ** lambda_power
    param_C = 1/(2*lambda_value) 
    param = parameter('-s 0 -c {} -e 0.000001 -q'.format(param_C))
    model = train(prob, param)
    p_label, p_acc, p_val = predict(y, x, model)
    err = error(y, p_label)
    print("0/1 error: ", err)
    print()
    results.append({'lambda': lambda_power, 'error': err})

ans, min_err = None, 1
for i in results:
    if i['error'] <= min_err:
        min_err = i['error']
        ans = i

print("the largest lambda: {}, log_10(lambda*): {}".format(10**ans['lambda'], ans['lambda']))