# import sys
# sys.path.append('C:\\Users\\Moritz Eck\\code\\fs18\\intro_ml\\shared')
import reader
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import KFold, RepeatedKFold, train_test_split
# FILE PATH: TRAINING FILE
FILE_PATH_TRAIN = "train1a.csv"
TEST_SIZE = 0.2
# alpha parameter values
alphas = [0.1, 1.0, 10.0, 100.0, 1000.0]
# training data
data = reader.read_csv(FILE_PATH_TRAIN, show_info=False)
# drop the first column
data = pd.DataFrame.drop(data, columns='Id')
# x-values
X = pd.DataFrame(
data,
columns=['x1', 'x2', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x9', 'x10'],
copy=True)
X = X.values
# y-values
Y = pd.DataFrame(data, columns=['y'], copy=True)
Y = Y['y'].values
#!/usr/bin/python import sys from zip import unzip from network import dl_file from reader import read_csv, read_last_line from pprint import pprint # variables url = "http://www.bclc.com/documents/DownloadableNumbers/CSV/649.zip" data_path = "data/" file_name = "649" # download zip file and save dl_file(url, data_path, file_name) # unzip to csv unzip(data_path, file_name) # read csv #read_last_line(data_path, file_name) reader = read_csv(data_path, file_name)
import reader
from sklearn.linear_model import ElasticNetCV
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import KFold, train_test_split
# file path constants
FILE_PATH_TRAIN = "train1b.csv"
# feature transformation functions
functions = [
lambda x: float(x), lambda x: math.pow(x, 2), lambda x: math.exp(x),
lambda x: math.cos(x), lambda x: float(1)
]
# read input data
data = reader.read_csv(FILE_PATH_TRAIN, False)
# drop the first column
data = pd.DataFrame.drop(data, columns='Id')
# splitting the data set into x & y values
# y-values
Y = pd.DataFrame(data, columns=['y'], copy=True)
Y = Y['y'].values
# x-values
X = pd.DataFrame(data, columns=['x1', 'x2', 'x3', 'x4', 'x5'], copy=True)
# new data frames for feature transformations
quad = pd.DataFrame(data, columns=['x6', 'x7', 'x8', 'x9', 'x10'])
exp = pd.DataFrame(data, columns=['x11', 'x12', 'x13', 'x14', 'x15'])
from id3 import ID3
from reader import read_csv
from c45 import C45
from c45_numeric_handler import process_numeric
from Rule import Rule
if __name__ == "__main__":
data = read_csv('Bagian B/datasets/iris.csv')
# print(data)
label = data[0, 0:-1].tolist()
x = data[1:, 0:-1]
target = data[1:, -1:].flatten()
# print(label)
# print(x)
# print(target)
# ID3
print("=====ID 3=====")
id3 = ID3()
id3.label = label
id3.fit(x, target)
# print(id3.tree)
# C45
print("=====C45=====")
c45 = C45()
c45.label = label
# print(x)
# print(target)
c45.fit(x, target)
# print(c45.tree)
from sklearn.preprocessing import StandardScaler
import numpy as np
import pandas as pd
import math
import sys
# personal csv reader module
import reader
FILE_PATH_TRAIN = "./input/train.csv"
FILE_PATH_TEST = "./input/test.csv"
TEST_SIZE = 0.225
# read training file
test_data = reader.read_csv(FILE_PATH_TEST, show_info=False)
training_data = reader.read_csv(FILE_PATH_TRAIN, show_info=False)
# splitting the training data set into x and y components
data_columns = [
'x1', 'x2', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x9', 'x10', 'x11', 'x12',
'x13', 'x14', 'x15', 'x16'
]
# test data
# extracting the x-values
x_values_test = test_data[data_columns]
x_values_test = x_values_test.values
# training data
# extracting the x-values
for i in range(len(ruleset)):
subs = powerset(ruleset[i]['rules'])
max_sub_acc = 0
max_sub = None
for sub in subs:
ruleset[i]['rules'] = sub
temp_acc = c45.predict_from_rule_set(x_test, y_test, ruleset,
label, default_value)
if max_sub_acc < temp_acc:
max_sub_acc = temp_acc
max_sub = sub
ruleset[i]['rules'] = max_sub
if __name__ == "__main__":
data = read_csv('play_tennis.csv')
label = data[0, 1:-1].tolist()
training_label = label.copy()
x = data[1:, 1:-1]
target = data[1:, -1:].flatten()
x_test, y_test, x_train, y_train = C45.train_test_split(x, target)
c45 = C45()
c45.tree = c45.fit(x_train, label, y_train)
default_value = mode(target)
print(default_value)
print(c45.tree)
ruleset = c45.tree.to_rule_list()
print(x_test)
print(ruleset)
c45.prune(x_test, y_test, ruleset, label, default_value)
# filename prefixes
FILE_PREFIX_XGB = "../output/xgb/task2_xgb_nativ_["
FILE_PREFIX_MLP = "../output/mlp_lbgfs/task2_mlp_lbgfs_["
# filename suffix
FILE_SUFFIX = "].csv"
# last file index e.g. [5]
INDEX_LAST_FILE = 6
# read training file
files = []
# read all existing files
for i in range(1, INDEX_LAST_FILE + 1):
files.append(reader.read_csv(FILE_PREFIX_MLP + str(i) + FILE_SUFFIX, False))
rows = []
# create a list for all values of the same row
for i in range(0, 3000):
row = []
for file in files:
row.append(file.iloc[i][1])
rows.append(row)
average_values = []
for i in range(0, 3000):
import reader as r
import sys as s
def plot_it(x, size):
y = x[1:] + [x[-1]]
plt.scatter(x, y, marker='p')
plt.show()
return True
def histogram(x, y, xlabel, ylabel):
plt.plot(x, y, color='red')
plt.bar(x, y, width=0.5)
plt.xlabel(xlabel)
plt.ylabel(ylabel)
plt.show()
return True
if __name__ == '__main__':
try:
assert (len(s.argv) >= 2)
except:
print("Please insert file name")
print("May be specified is reside in your system")
x = r.read_csv(s.argv[1])
plot_it(x, len(x))
x, y = frequency_calc(x, int(s.argv[2]))
histogram(x, y, "x_axis", "y_axis")
def tessplot_csv(fname, ax=None, time_format='BJD_TDB'):
time, y, yerr = read_csv(fname)
return tessplot(time, y, yerr, ax=ax, time_format=time_format)
def brokenplot_csv(fname, dt=10, ax=None, time_format='BJD_TDB'):
time, y, yerr = read_csv(fname)
return brokenplot(time, y, yerr, dt=dt, ax=ax, time_format=time_format)
#from stock import Stock
import reader
class Stock(object):
...
def __eq__(self, other):
return ((self.name, self.shares, self.price) ==
(other.name, other.shares, other.price))
def __lt__(self, other):
return ((self.name, self.shares, self.price) <
(other.name, other.shares, other.price))
def __le__(self, other):
return ((self.name, self.shares, self.price) <=
(other.name, other.shares, other.price))
#s = MyStock('GOOG', 100, 490.1)
#print (s)
portfolio = reader.read_csv(stock.Stock, 'C:\\Users\\kathiria\\Desktop\\Advanced Python\\pythonmaster\\pythonmaster\\Data\\portfolio.csv')
print("*"*50)
print(portfolio)
print("*"*50)
portfolio.sort()
from sklearn.metrics import accuracy_score
import numpy as np
import pandas as pd
import reader
# file paths
XGB_CMP_FILEPATH = "../output/xgb/average/task2_xgb_nativ_av[1-6].csv"
MLP_CMP_FILEPATH = "../output/mlp_lbgfs/average/task2_mlp_lbgfs_av[1-6].csv"
# read comparison files
xgb_cmp_file = reader.read_csv(XGB_CMP_FILEPATH, False)['y'].values
mlp_cmp_file = reader.read_csv(MLP_CMP_FILEPATH, False)['y'].values
# filename prefixes
FILE_PREFIX_XGB = "../output/xgb/task2_xgb_nativ_["
FILE_PREFIX_MLP = "../output/mlp_lbgfs/task2_mlp_lbgfs_["
# filename suffix
FILE_SUFFIX = "].csv"
# read training file
xgb_files = []
mlp_files = []
# read all existing xgb files
for i in range(1, 9):
xgb_files.append(
reader.read_csv(FILE_PREFIX_XGB + str(i) + FILE_SUFFIX,
False)['y'].values)
import calulation as c
from sys import version_info
import csv
import reader as r
if __name__ == '__main__':
if version_info[0] >= 3:
file_name = input("Enter data file name : ")
else:
file_name = raw_input("Enter data file name :")
interval = int(input("Enter interval : "))
#print("File name is :{} and interval is {}".format(file_name,interval))
try:
ls = r.read_csv(file_name)
except IOError as e:
print(str(e))
res = c.uniform_chi_square_test(ls, len(ls), interval)
r.print_tab(res)
