How To Load Files Into Python?

Data can be read from a number of sources, including files and databases, using Python. The.txt and.csv file types are two that are frequently utilised. Using either the Python CSV library or built-in import and export capabilities, you can import and export files. 

How to Import Data into Python? 

First we need to import the data into python. Importing the data as a dataframe helps us to handle the data much easily. The pandas module of Python is specially made to handle data as a data frame.

What are the Different Data Types in Python?

These are the 14 file types that can be opened by Pandas.

Comma-separated values (CSV)

pandas.read_csv(filepath_or_buffer, sep=NoDefault.no_default, delimiter=None, header='infer', names=NoDefault.no_default, index_col=None, usecols=None, squeeze=None, prefix=NoDefault.no_default, mangle_dupe_cols=True, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=None, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression='infer', thousands=None, decimal='.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, encoding_errors='strict', dialect=None, error_bad_lines=None, warn_bad_lines=None, on_bad_lines=None, delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None, storage_options=None)

import pandas as pd

pd.read_csv('sometext.csv')

XLSX

pandas.read_excel(io, sheet_name=0, header=0, names=None, index_col=None, usecols=None, squeeze=None, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skiprows=None, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, parse_dates=False, date_parser=None, thousands=None, decimal='.', comment=None, skipfooter=0, convert_float=None, mangle_dupe_cols=True, storage_options=None)

import pandas as pd

pd.read_excel('someexcelfile.xlsx')

Zip file

import zipfile

import pandas as pd

# read the dataset using the compression zip

df = pd.read_csv('test.zip',compression='zip')

# display dataset

print(df.head())

Plain Text (txt)

# importing pandas

import pandas as pd  

# read text file into pandas DataFrame

df = pd.read_csv("gfg.txt", sep=" ")

# display DataFrame

print(df)

JSON

import pandas as pd

file_df = pd.read_json('E:/datasets/filename.json')

file_df.head()

XML

import xml.etree.ElementTree as ET

import pandas as pd

xml_data=open('filename.xml','r').read()

root=ET.XML(xml_data)  

data=[]

cols = []

for i, child in enumerate(root):

    data.append([subchild.text for subchild in child])

    cols.append(child.tag)

df = pd. DataFrame(data).T

df.columns=cols

print(df)

HTML

import pandas as pd

from unicodedata import normalize

table_MN=pd.read_html('https://en.wikipedia.org/wiki/something')

Images

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

#create an image

imar = np.array([[[1.,0.],[0.,0.]],

                 [[0.,1.],[0.,1.]],

                 [[0.,0.],[1.,1.]]]).transpose()

plt.imsave('pic.jpg', imar)

#create dataframe

df = pd.DataFrame([[0,""]], columns=["Feature1","Feature2"])

# read the image

im = plt.imread('pic.jpg')

plt.imshow(im)

plt.show()

Hierachial Data Format

import pandas as pd

subjectsdata = {'Name': ['sravan', 'sravan', 'sravan', 'sravan',

                         'sravan', 'sravan', 'sravan', 'sravan',

                         'Ojaswi', 'Ojaswi', 'Ojaswi', 'Ojaswi',

                         'Ojaswi', 'Ojaswi', 'Ojaswi', 'Ojaswi',

                         'Rohith', 'Rohith', 'Rohith', 'Rohith',

                         'Rohith', 'Rohith', 'Rohith', 'Rohith'],

                  

                'college': ['VFSTRU', 'VFSTRU', 'VFSTRU', 'VFSTRU',

                            'VFSTRU', 'VFSTRU', 'VFSTRU', 'VFSTRU',

                            'VIT', 'VIT', 'VIT', 'VIT', 'VIT', 'VIT',

                            'VIT', 'VIT', 'IIT-Bhu', 'IIT-Bhu', 'IIT-Bhu',

                            'IIT-Bhu', 'IIT-Bhu', 'IIT-Bhu', 'IIT-Bhu',

                            'IIT-Bhu'],

                  

                'subject': ['java', 'dbms', 'dms', 'coa', 'python', 'dld',

                            'android', 'iot', 'java', 'dbms', 'dms', 'coa',

                            'python', 'dld', 'android', 'iot', 'java',

                            'dbms', 'dms', 'coa', 'python', 'dld', 'android',

                            'iot']

                }

df = pd.DataFrame(subjectsdata)

print(df)

PDF

from tabula import read_pdf

df = read_pdf('data.pdf')

DOCX

pip install pandas

pip install python-docx

import pandas as pd

from docx import Documentdocument = Document("<<docx file path>>")

data = [[cell.text for cell in row.cells] for row in table.rows]

df = pd.DataFrame(data)

MP3

import librosa

song_path = 'track1.mp3'

y,sr = librosa.load(song_path,sr=22050)

print(y)

This would be stored as a numpy array

MP4

import pylab

import imageio

filename = '/tmp/file.mp4'

vid = imageio.get_reader(filename,  'ffmpeg')

nums = [10, 287]

for num in nums:

    image = vid.get_data(num)

    fig = pylab.figure()

    fig.suptitle('image #{}'.format(num), fontsize=20)

    pylab.imshow(image)

pylab.show()

SQL

pandas.read_sql(sql, con, index_col=None, coerce_float=True, params=None, parse_dates=None, columns=None, chunksize=None)