normalize_utils 

 1import pandas as pd
 2import numpy as np
 3import sys
 4import matplotlib.pyplot as plt
 5import os
 6
 7"""File containing code used as utility to normalize files, vector, etc"""
 8
 9def getFileName(argument):
10    """Given a full path name, returns only the name of the file"""
11    index = argument.rfind('/')
12    return argument[index:] 
13
14def normalizeFile(filename, des_path, source_path):
15    """Normalize an entire file"""
16    dataframe = pd.read_csv(source_path + filename, index_col=0)
17    dataframe.plot(title=f"{filename}")
18
19    data_array = []
20
21    max_value = 0
22    min_value = 999999999
23
24    for index,row in dataframe.iterrows():
25        data_array.append(row[0])
26        if row[0] > max_value:
27            max_value = row[0]
28        if row[0] < min_value:
29            min_value = row[0]
30
31    normalized_data_array = []
32
33    for value in data_array:
34        normalized_value = (value - min_value) / (max_value - min_value)
35        normalized_data_array.append(normalized_value)
36
37    normalized_data_dict = {"Precio": normalized_data_array}
38
39    normalized_dataframe = pd.DataFrame(normalized_data_dict)
40    normalized_dataframe.plot()
41
42    normalized_dataframe.to_csv(des_path + filename)
43
44def normalizeVector(vector):
45    """Normalize a given vector with max min normalization"""
46    max_number = 0
47    min_number = 99999999
48    for number in vector:
49        number = float(number)
50        if number > max_number:
51            max_number = number
52        if number < min_number:
53            min_number = number
54    
55    normalized_vector = []
56
57    for number in vector:
58        number = float(number)
59        normalized_number = (number - min_number) / (max_number - min_number)
60        normalized_vector.append(round(normalized_number, 3))
61
62    return normalized_vector
63
64# file_list = os.listdir(sys.argv[1])
65# for file in file_list:
66#     normalizeFile(file, sys.argv[2], sys.argv[1])
67# plt.show()
def getFileName(argument) 
10def getFileName(argument):
11    """Given a full path name, returns only the name of the file"""
12    index = argument.rfind('/')
13    return argument[index:]

Given a full path name, returns only the name of the file

def normalizeFile(filename, des_path, source_path) 
15def normalizeFile(filename, des_path, source_path):
16    """Normalize an entire file"""
17    dataframe = pd.read_csv(source_path + filename, index_col=0)
18    dataframe.plot(title=f"{filename}")
19
20    data_array = []
21
22    max_value = 0
23    min_value = 999999999
24
25    for index,row in dataframe.iterrows():
26        data_array.append(row[0])
27        if row[0] > max_value:
28            max_value = row[0]
29        if row[0] < min_value:
30            min_value = row[0]
31
32    normalized_data_array = []
33
34    for value in data_array:
35        normalized_value = (value - min_value) / (max_value - min_value)
36        normalized_data_array.append(normalized_value)
37
38    normalized_data_dict = {"Precio": normalized_data_array}
39
40    normalized_dataframe = pd.DataFrame(normalized_data_dict)
41    normalized_dataframe.plot()
42
43    normalized_dataframe.to_csv(des_path + filename)

Normalize an entire file

def normalizeVector(vector) 
45def normalizeVector(vector):
46    """Normalize a given vector with max min normalization"""
47    max_number = 0
48    min_number = 99999999
49    for number in vector:
50        number = float(number)
51        if number > max_number:
52            max_number = number
53        if number < min_number:
54            min_number = number
55    
56    normalized_vector = []
57
58    for number in vector:
59        number = float(number)
60        normalized_number = (number - min_number) / (max_number - min_number)
61        normalized_vector.append(round(normalized_number, 3))
62
63    return normalized_vector

Normalize a given vector with max min normalization