practical-ml-w-python/Code_Ch 03/code/read_csv.py at master · irfa50/practical-ml-w-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# -*- coding: utf-8 -*-
"""
Created on Wed May 10 19:51:47 2017

@author: Raghav Bali
"""

"""

This script showcases methods to extract data from CSVs:
    + csv containing delimiter separated values
    + csv containing tabular data

using csv and pandas packages

``Execute``
        $ python read_csv.py

"""

import csv
import pandas as pd
from pprint import pprint

def print_basic_csv(file_name, delimiter=','):
    """This function extracts and prints csv content from given filename
       Details: https://docs.python.org/2/library/csv.html
    Args:
        file_name (str): file path to be read
        delimiter (str): delimiter used in csv. Default is comma (',')

    Returns:
        None

    """
    csv_rows = list()
    csv_attr_dict = dict()
    csv_reader = None

    # read csv
    csv_reader = csv.reader(open(file_name, 'r'), delimiter=delimiter)

    # iterate and extract data
    for row in csv_reader:
        print(row)
        csv_rows.append(row)

    # prepare attribute lists
    for col in csv_rows[0]:
        csv_attr_dict[col]=list()

    # iterate and add data to attribute lists
    for row in csv_rows[1:]:
        csv_attr_dict['sno'].append(row[0])
        csv_attr_dict['fruit'].append(row[1])
        csv_attr_dict['color'].append(row[2])
        csv_attr_dict['price'].append(row[3])

    # print the result
    print("\n\n")
    print("CSV Attributes::")
    pprint(csv_attr_dict)


def print_tabular_data(file_name,delimiter=","):
    """This function extracts and prints tabular csv content from given filename
       Details: http://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html
    Args:
        file_name (str): file path to be read
        delimiter (str): delimiter used in csv. Default is comma ('\t')

    Returns:
        None

    """
    df = pd.read_csv(file_name,sep=delimiter)
    print(df)


if __name__=='__main__':
    print("\n\n")
    print("*"*30)
    print("Contents of sample csv file:")
    print("*"*30)
    print_basic_csv(r'tabular_csv.csv')

    print("\n\n")
    print("*"*30)
    print("Contents of a tabular csv file:")
    print("*"*30)
    print_tabular_data(r'tabular_csv.csv')