Welcome to 30 Days ML

How to upload / Import Data

In [6]: # pandas
import pandas as pd

In [7]: pd.read_csv('hotel_bookings.csv')

Out[7]: hotel is_canceled lead_time arrival_date_year arrival_date_month arrival_date_week_num

Resort
0 0 342 2015 July
Hotel

Resort
1 0 737 2015 July
Hotel

Resort
2 0 7 2015 July
Hotel

Resort
3 0 13 2015 July
Hotel

Resort
4 0 14 2015 July
Hotel

... ... ... ... ... ...

City
119385 0 23 2017 August
Hotel

City
119386 0 102 2017 August
Hotel

City
119387 0 34 2017 August
Hotel

City
119388 0 109 2017 August
Hotel

City
119389 0 205 2017 August
Hotel

119390 rows × 32 columns

Gathering Data With CSV

In [8]: import pandas as pd

In [9]: df = pd.read_csv('aug_train.csv')

In [10]: df
Out[10]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

3. Opening a csv file from an URL

In [11]: import requests
from io import StringIO
url = "https://raw.githubusercontent.com/cs109/2014_data/master/countries.csv"
headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:66.0) Ge
req = requests.get(url, headers=headers)
data = StringIO(req.text)
pd.read_csv(data)
Out[11]: Country Region

0 Algeria AFRICA

1 Angola AFRICA

2 Benin AFRICA

3 Botswana AFRICA

4 Burkina AFRICA

... ... ...

189 Paraguay SOUTH AMERICA

190 Peru SOUTH AMERICA

191 Suriname SOUTH AMERICA

192 Uruguay SOUTH AMERICA

193 Venezuela SOUTH AMERICA

194 rows × 2 columns

4. Sep Parameter
In [12]: pd.read_csv('movie_titles_metadata.tsv')

Out[12]: m0\t10 things i hate about you\t1999\t6.90\t62847\t['comedy' 'romance']

0 m1\t1492: conquest of paradise\t1992\t6.20\t10...

1 m2\t15 minutes\t2001\t6.10\t25854\t['action' '...

2 m3\t2001: a space odyssey\t1968\t8.40\t163227\...

3 m4\t48 hrs.\t1982\t6.90\t22289\t['action' 'com...

4 m5\tthe fifth element\t1997\t7.50\t133756\t['a...

... ...

611 m612\twatchmen\t2009\t7.80\t135229\t['action' ...

612 m613\txxx\t2002\t5.60\t53505\t['action' 'adven...

613 m614\tx-men\t2000\t7.40\t122149\t['action' 'sc...

614 m615\tyoung frankenstein\t1974\t8.00\t57618\t[...

615 m616\tzulu dawn\t1979\t6.40\t1911\t['action' '...

616 rows × 1 columns

In [13]: pd.read_csv('movie_titles_metadata.tsv',sep='\t')
Out[13]: 10 things i hate about
m0 1999 6.90 62847 ['comedy' 'romance']
you

1492: conquest of ['adventure' 'biography' 'drama'

0 m1 1992 6.2 10421.0
paradise 'history']

1 m2 15 minutes 2001 6.1 25854.0 ['action' 'crime' 'drama' 'thriller']

2 m3 2001: a space odyssey 1968 8.4 163227.0 ['adventure' 'mystery' 'sci-fi']

['action' 'comedy' 'crime' 'drama'

3 m4 48 hrs. 1982 6.9 22289.0
'thriller']

['action' 'adventure' 'romance' 'sci-fi'

4 m5 the fifth element 1997 7.5 133756.0
'thri...

... ... ... ... ... ... ...

['action' 'crime' 'fantasy' 'mystery' 'sci-

611 m612 watchmen 2009 7.8 135229.0
fi'...

612 m613 xxx 2002 5.6 53505.0 ['action' 'adventure' 'crime']

613 m614 x-men 2000 7.4 122149.0 ['action' 'sci-fi']

614 m615 young frankenstein 1974 8.0 57618.0 ['comedy' 'sci-fi']

['action' 'adventure' 'drama' 'history'

615 m616 zulu dawn 1979 6.4 1911.0
'war']

616 rows × 6 columns

In [14]: pd.read_csv('movie_titles_metadata.tsv',sep='\t',names=['sno','name','release_year'

Out[14]: sno name release_year rating votes genres

10 things i hate about

0 m0 1999 6.9 62847.0 ['comedy' 'romance']
you

1492: conquest of ['adventure' 'biography' 'drama'

1 m1 1992 6.2 10421.0
paradise 'history']

2 m2 15 minutes 2001 6.1 25854.0 ['action' 'crime' 'drama' 'thriller']

3 m3 2001: a space odyssey 1968 8.4 163227.0 ['adventure' 'mystery' 'sci-fi']

['action' 'comedy' 'crime' 'drama'

4 m4 48 hrs. 1982 6.9 22289.0
'thriller']

... ... ... ... ... ... ...

['action' 'crime' 'fantasy'

612 m612 watchmen 2009 7.8 135229.0
'mystery' 'sci-fi'...

613 m613 xxx 2002 5.6 53505.0 ['action' 'adventure' 'crime']

614 m614 x-men 2000 7.4 122149.0 ['action' 'sci-fi']

615 m615 young frankenstein 1974 8.0 57618.0 ['comedy' 'sci-fi']

['action' 'adventure' 'drama'

616 m616 zulu dawn 1979 6.4 1911.0
'history' 'war']

617 rows × 6 columns

5. Index_col parameter
In [15]: pd.read_csv('aug_train.csv')

Out[15]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

6. Header parameter
In [18]: pd.read_csv('test.csv')

Out[18]: Unnamed: Unnamed: Unnamed: Unnamed:

Unnamed: 3 Unnamed: 5 U
0 1 2 4

0 0 enrollee_id city city_development_index gender relevent_experience enrolled

No relevent
1 1 29725 city_40 0.776 Male no_
experience

No relevent
2 2 11561 city_21 0.624 NaN Full t
experience

No relevent
3 3 33241 city_115 0.789 NaN
experience

Has relevent
4 4 666 city_162 0.767 Male no_
experience

In [19]: pd.read_csv('test.csv',header=1)
Out[19]: 0 enrollee_id city city_development_index gender relevent_experience enrolled_university

No relevent
0 1 29725 city_40 0.776 Male no_enrollmen
experience

No relevent
1 2 11561 city_21 0.624 NaN Full time cours
experience

No relevent
2 3 33241 city_115 0.789 NaN NaN
experience

Has relevent
3 4 666 city_162 0.767 Male no_enrollmen
experience

7. Use_col parameter
In [20]: pd.read_csv('aug_train.csv',usecols=['enrollee_id','gender','education_level'])

Out[20]: enrollee_id gender education_level

0 8949 Male Graduate

1 29725 Male Graduate

2 11561 NaN Graduate

3 33241 NaN Graduate

4 666 Male Masters

... ... ... ...

19153 7386 Male Graduate

19154 31398 Male Graduate

19155 24576 Male Graduate

19156 5756 Male High School

19157 23834 NaN Primary School

19158 rows × 3 columns

8. Squeeze parameters
In [27]: pd.read_csv('aug_train.csv',usecols=['gender'],squeeze=True)

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[27], line 1
----> 1 pd.read_csv('aug_train.csv',usecols=['enrolle_id'],squeeze=True)

TypeError: read_csv() got an unexpected keyword argument 'squeeze'

9. Skiprows/nrows Parameter
In [28]: pd.read_csv('aug_train.csv')
Out[28]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

In [29]: pd.read_csv('aug_train.csv',skiprows=[0,1])
Out[29]: No
29725 city_40 0.7759999999999999 Male relevent no_enrollment Graduate ST
experience

No
Full time
0 11561 city_21 0.624 NaN relevent Graduate ST
course
experience

No
Busin
1 33241 city_115 0.789 NaN relevent NaN Graduate
Deg
experience

Has
2 666 city_162 0.767 Male relevent no_enrollment Masters ST
experience

Has
Part time
3 21651 city_176 0.764 NaN relevent Graduate ST
course
experience

Has
High
4 28806 city_160 0.920 Male relevent no_enrollment N
School
experience

... ... ... ... ... ... ... ...

No
19151 7386 city_173 0.878 Male relevent no_enrollment Graduate Humani
experience

Has
19152 31398 city_103 0.920 Male relevent no_enrollment Graduate ST
experience

Has
19153 24576 city_103 0.920 Male relevent no_enrollment Graduate ST
experience

Has
High
19154 5756 city_65 0.802 Male relevent no_enrollment N
School
experience

No
Primary
19155 23834 city_67 0.855 NaN relevent no_enrollment N
School
experience

19156 rows × 14 columns

In [30]: pd.read_csv('aug_train.csv',skiprows=[5,6])
Out[30]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 28806 city_160 0.920 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19151 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19152 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19153 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19154 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19155 23834 city_67 0.855 NaN no_enrollme
experience

19156 rows × 14 columns

In [31]: pd.read_csv('aug_train.csv',nrows=100)
Out[31]: enrollee_id city city_development_index gender relevent_experience enrolled_university

Has relevent
0 8949 city_103 0.920 Male no_enrollment
experience

No relevent
1 29725 city_40 0.776 Male no_enrollment
experience

No relevent
2 11561 city_21 0.624 NaN Full time course
experience

No relevent
3 33241 city_115 0.789 NaN NaN
experience

Has relevent
4 666 city_162 0.767 Male no_enrollment
experience

... ... ... ... ... ... ...

Has relevent
95 12081 city_65 0.802 Male Full time course
experience

No relevent
96 7364 city_160 0.920 NaN Full time course
experience

No relevent
97 11184 city_74 0.579 NaN Full time course
experience

Has relevent
98 7016 city_65 0.802 Male no_enrollment
experience

Has relevent
99 8695 city_11 0.550 Male no_enrollment
experience

100 rows × 14 columns

10. Encoding parameter

In [32]: pd.read_csv('zomato.csv')
---------------------------------------------------------------------------
UnicodeDecodeError Traceback (most recent call last)
Cell In[32], line 1
----> 1 pd.read_csv('zomato.csv')

File ~\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:912, in read_csv(f

ilepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engin
e, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter,
nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dat
es, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cach
e_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quo
techar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dial
ect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, stor
age_options, dtype_backend)
899 kwds_defaults = _refine_defaults_read(
900 dialect,
901 delimiter,
(...)
908 dtype_backend=dtype_backend,
909 )
910 kwds.update(kwds_defaults)
--> 912 return _read(filepath_or_buffer, kwds)

File ~\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:577, in _read(file

path_or_buffer, kwds)
574 _validate_names(kwds.get("names", None))
576 # Create the parser.
--> 577 parser = TextFileReader(filepath_or_buffer, **kwds)
579 if chunksize or iterator:
580 return parser

File ~\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:1407, in TextFileR

eader.__init__(self, f, engine, **kwds)
1404 self.options["has_index_names"] = kwds["has_index_names"]
1406 self.handles: IOHandles | None = None
-> 1407 self._engine = self._make_engine(f, self.engine)

File ~\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:1679, in TextFileR

eader._make_engine(self, f, engine)
1676 raise ValueError(msg)
1678 try:
-> 1679 return mapping[engine](f, **self.options)
1680 except Exception:
1681 if self.handles is not None:

File ~\anaconda3\Lib\site-packages\pandas\io\parsers\c_parser_wrapper.py:93, in CP
arserWrapper.__init__(self, src, **kwds)
90 if kwds["dtype_backend"] == "pyarrow":
91 # Fail here loudly instead of in cython after reading
92 import_optional_dependency("pyarrow")
---> 93 self._reader = parsers.TextReader(src, **kwds)
95 self.unnamed_cols = self._reader.unnamed_cols
97 # error: Cannot determine type of 'names'

File ~\anaconda3\Lib\site-packages\pandas\_libs\parsers.pyx:550, in pandas._libs.p

arsers.TextReader.__cinit__()

File ~\anaconda3\Lib\site-packages\pandas\_libs\parsers.pyx:639, in pandas._libs.p

arsers.TextReader._get_header()

File ~\anaconda3\Lib\site-packages\pandas\_libs\parsers.pyx:850, in pandas._libs.p

arsers.TextReader._tokenize_rows()

File ~\anaconda3\Lib\site-packages\pandas\_libs\parsers.pyx:861, in pandas._libs.p

 arsers.TextReader._check_tokenize_status()

File ~\anaconda3\Lib\site-packages\pandas\_libs\parsers.pyx:2021, in pandas._libs.

parsers.raise_parser_error()

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xed in position 7044: invalid
continuation byte

In [33]: pd.read_csv('zomato.csv',encoding='latin-1')
Out[33]:
Restaurant Restaurant Country Locality
City Address Locality L
ID Name Code Verbose

Third Floor, Century City

Century City
Century City Mall,
Le Petit Mall,
0 6317637 162 Makati City Mall, Poblacion, 12
Souffle Poblacion,
Kalayaan Makati City,
Makati City
Avenu... Mak...

Little Tokyo, Little Tokyo,

Little Tokyo,
2277 Chino Legaspi
Izakaya Legaspi
1 6304287 162 Makati City Roces Village, 12
Kikufuji Village,
Avenue, Makati City,
Makati City
Legaspi... Ma...

Edsa
Edsa Shangri- Edsa Shangri-
Shangri-La, 1
Heat - Edsa Mandaluyong La, Ortigas, La, Ortigas,
2 6300002 162 Garden Way, 12
Shangri-La City Mandaluyong Mandaluyong
Ortigas,
City City, Ma...
Mandal...

Third Floor, SM
SM
Mega Megamall,
Megamall,
Mandaluyong Fashion Hall, Ortigas,
3 6318506 Ooma 162 Ortigas, 12
City SM Mandaluyong
Mandaluyong
Megamall, City,
City
O... Mandal...

SM
Third Floor, SM
Megamall,
Mega Megamall,
Sambo Mandaluyong Ortigas,
4 6314302 162 Atrium, SM Ortigas, 12
Kojin City Mandaluyong
Megamall, Mandaluyong
City,
Ortigas... City
Mandal...

... ... ... ... ... ... ... ...

Kemankeô
Karamustafa
NamlÛ± Karakí_y,
9546 5915730 208 ÛÁstanbul Paôa Karakí_y 2
Gurme ÛÁstanbul
Mahallesi,
RÛ±htÛ±...

Koôuyolu
Mahallesi,
Ceviz Koôuyolu,
9547 5908749 208 ÛÁstanbul Muhittin Koôuyolu 2
AÛôacÛ± ÛÁstanbul
íìstí_ndaÛô
Cadd...

Kuruí_eôme
Mahallesi, Kuruí_eôme,
9548 5915807 Huqqa 208 ÛÁstanbul Kuruí_eôme 2
Muallim Naci ÛÁstanbul
Caddesi, N...

Kuruí_eôme
Aôôk Mahallesi, Kuruí_eôme,
9549 5916112 208 ÛÁstanbul Kuruí_eôme 2
Kahve Muallim Naci ÛÁstanbul
Caddesi, N...

CafeaÛôa
Walter's Mahallesi,
Moda,
9550 5927402 Coffee 208 ÛÁstanbul BademaltÛ± Moda 2
ÛÁstanbul
Roastery Sokak, No
21/B,...
 9551 rows × 21 columns

11. Skip bad lines

In [34]: pd.read_csv('zomato.csv', address=';', encoding="latin-1")

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[34], line 1
----> 1 pd.read_csv('zomato.csv', address=';', encoding="latin-1")

TypeError: read_csv() got an unexpected keyword argument 'address'

In [35]: pd.read_csv('zomato.csv', address=';', encoding="latin-1",error_bad_lines=False)

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[35], line 1
----> 1 pd.read_csv('zomato.csv', address=';', encoding="latin-1",error_bad_lines=
False)

TypeError: read_csv() got an unexpected keyword argument 'address'

12.dtypes parameter
In [37]: pd.read_csv('aug_train.csv').info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 19158 entries, 0 to 19157
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 enrollee_id 19158 non-null int64
1 city 19158 non-null object
2 city_development_index 19158 non-null float64
3 gender 14650 non-null object
4 relevent_experience 19158 non-null object
5 enrolled_university 18772 non-null object
6 education_level 18698 non-null object
7 major_discipline 16345 non-null object
8 experience 19093 non-null object
9 company_size 13220 non-null object
10 company_type 13018 non-null object
11 last_new_job 18735 non-null object
12 training_hours 19158 non-null int64
13 target 19158 non-null float64
dtypes: float64(2), int64(2), object(10)
memory usage: 2.0+ MB

In [38]: pd.read_csv('aug_train.csv',dtype={'target':int}).info()
 <class 'pandas.core.frame.DataFrame'>
RangeIndex: 19158 entries, 0 to 19157
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 enrollee_id 19158 non-null int64
1 city 19158 non-null object
2 city_development_index 19158 non-null float64
3 gender 14650 non-null object
4 relevent_experience 19158 non-null object
5 enrolled_university 18772 non-null object
6 education_level 18698 non-null object
7 major_discipline 16345 non-null object
8 experience 19093 non-null object
9 company_size 13220 non-null object
10 company_type 13018 non-null object
11 last_new_job 18735 non-null object
12 training_hours 19158 non-null int64
13 target 19158 non-null int32
dtypes: float64(1), int32(1), int64(2), object(10)
memory usage: 2.0+ MB

13. Handling Dates

In [39]: pd.read_csv('IPL Matches 2008-2020.csv').info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 816 entries, 0 to 815
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 id 816 non-null int64
1 city 803 non-null object
2 date 816 non-null object
3 player_of_match 812 non-null object
4 venue 816 non-null object
5 neutral_venue 816 non-null int64
6 team1 816 non-null object
7 team2 816 non-null object
8 toss_winner 816 non-null object
9 toss_decision 816 non-null object
10 winner 812 non-null object
11 result 812 non-null object
12 result_margin 799 non-null float64
13 eliminator 812 non-null object
14 method 19 non-null object
15 umpire1 816 non-null object
16 umpire2 816 non-null object
dtypes: float64(1), int64(2), object(14)
memory usage: 108.5+ KB

In [40]: pd.read_csv('IPL Matches 2008-2020.csv',parse_dates=['date']).info()

 <class 'pandas.core.frame.DataFrame'>
RangeIndex: 816 entries, 0 to 815
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 id 816 non-null int64
1 city 803 non-null object
2 date 816 non-null datetime64[ns]
3 player_of_match 812 non-null object
4 venue 816 non-null object
5 neutral_venue 816 non-null int64
6 team1 816 non-null object
7 team2 816 non-null object
8 toss_winner 816 non-null object
9 toss_decision 816 non-null object
10 winner 812 non-null object
11 result 812 non-null object
12 result_margin 799 non-null float64
13 eliminator 812 non-null object
14 method 19 non-null object
15 umpire1 816 non-null object
16 umpire2 816 non-null object
dtypes: datetime64[ns](1), float64(1), int64(2), object(13)
memory usage: 108.5+ KB

In [41]: pd.read_csv('IPL Matches 2008-2020.csv',parse_dates=['date']).info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 816 entries, 0 to 815
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 id 816 non-null int64
1 city 803 non-null object
2 date 816 non-null datetime64[ns]
3 player_of_match 812 non-null object
4 venue 816 non-null object
5 neutral_venue 816 non-null int64
6 team1 816 non-null object
7 team2 816 non-null object
8 toss_winner 816 non-null object
9 toss_decision 816 non-null object
10 winner 812 non-null object
11 result 812 non-null object
12 result_margin 799 non-null float64
13 eliminator 812 non-null object
14 method 19 non-null object
15 umpire1 816 non-null object
16 umpire2 816 non-null object
dtypes: datetime64[ns](1), float64(1), int64(2), object(13)
memory usage: 108.5+ KB

In [42]: pd.read_csv('IPL Matches 2008-2020.csv)

Cell In[42], line 1

pd.read_csv('IPL Matches 2008-2020.csv)
^
SyntaxError: unterminated string literal (detected at line 1)

14. Convertors
In [44]: pd.read_csv('IPL Matches 2008-2020.csv',converters={'team1':rename})
 ---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[44], line 1
----> 1 pd.read_csv('IPL Matches 2008-2020.csv',converters={'team1':rename})

NameError: name 'rename' is not defined

15. na_values parameter

In [45]: pd.read_csv('aug_train.csv')

Out[45]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

In [46]: pd.read_csv('aug_train.csv',na_values=['Male',])
Out[46]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 NaN no_enrollme
experience

No relevent
1 29725 city_40 0.776 NaN no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 NaN no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 NaN no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 NaN no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 NaN no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 NaN no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

16. Loading a huge dataset in chunks

In [47]: pd.read_csv('aug_train.csv')
Out[47]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

In [56]: dfs = pd.read_csv('aug_train.csv',chunksize=5000)

Cell In[56], line 2

for chunks in dfs:
^
SyntaxError: incomplete input

In [58]: for chunks in dfs:

print(chunk.shape)

---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[58], line 2
1 for chunks in dfs:
----> 2 print(chunk.shape)

NameError: name 'chunk' is not defined

In [59]: pd.read_csv('aug_train.csv')
Out[59]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

In [63]: dfs = pd.read_csv('aug_train.csv',chunksize=5000)

for chunks in dfs:

Cell In[63], line 2

for chunks in dfs:
^
SyntaxError: incomplete input

In [62]:

Cell In[62], line 1

for chunks in dfs:
^
SyntaxError: incomplete input

Working with JSON/SQL

In [64]: import pandas as pd

In [65]: pd.read_json('train.json')
Out[65]: id cuisine ingredients

0 10259 greek [romaine lettuce, black olives, grape tomatoes...

1 25693 southern_us [plain flour, ground pepper, salt, tomatoes, g...

2 20130 filipino [eggs, pepper, salt, mayonaise, cooking oil, g...

3 22213 indian [water, vegetable oil, wheat, salt]

4 13162 indian [black pepper, shallots, cornflour, cayenne pe...

... ... ... ...

39769 29109 irish [light brown sugar, granulated sugar, butter, ...

39770 11462 italian [KRAFT Zesty Italian Dressing, purple onion, b...

39771 2238 irish [eggs, citrus fruit, raisins, sourdough starte...

39772 41882 chinese [boneless chicken skinless thigh, minced garli...

39773 2362 mexican [green chile, jalapeno chilies, onions, ground...

39774 rows × 3 columns

In [66]: pd.read_json('https://api.exchangerate-api.com/v4/latest/INR')

Out[66]: provider WARNING_UPGRADE_TO_V6 terms base date

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

AED INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

AFN INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

ALL INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

AMD INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

ANG INR
api.com api.com/docs/free api.com/terms 11-23

... ... ... ... ... ..

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

XPF INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

YER INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

ZAR INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

ZMW INR
api.com api.com/docs/free api.com/terms 11-23

https://www.exchangerate- https://www.exchangerate- https://www.exchangerate- 2023-

ZWL INR
api.com api.com/docs/free api.com/terms 11-23

162 rows × 7 columns

Working with SQL

In [67]: !pip install mysql.connector

Collecting mysql.connector
Downloading mysql-connector-2.2.9.tar.gz (11.9 MB)
---------------------------------------- 0.0/11.9 MB ? eta -:--:--
---------------------------------------- 0.0/11.9 MB ? eta -:--:--
---------------------------------------- 0.1/11.9 MB 1.0 MB/s eta 0:00:12
--------------------------------------- 0.3/11.9 MB 1.5 MB/s eta 0:00:08
- -------------------------------------- 0.4/11.9 MB 1.9 MB/s eta 0:00:06
-- ------------------------------------- 0.6/11.9 MB 2.3 MB/s eta 0:00:05
-- ------------------------------------- 0.9/11.9 MB 2.7 MB/s eta 0:00:04
---- ----------------------------------- 1.4/11.9 MB 3.7 MB/s eta 0:00:03
------ --------------------------------- 1.9/11.9 MB 4.3 MB/s eta 0:00:03
------- -------------------------------- 2.2/11.9 MB 4.6 MB/s eta 0:00:03
--------- ------------------------------ 2.7/11.9 MB 4.8 MB/s eta 0:00:02
---------- ----------------------------- 3.0/11.9 MB 5.1 MB/s eta 0:00:02
----------- ---------------------------- 3.4/11.9 MB 5.2 MB/s eta 0:00:02
------------- -------------------------- 4.0/11.9 MB 5.6 MB/s eta 0:00:02
-------------- ------------------------- 4.3/11.9 MB 5.7 MB/s eta 0:00:02
--------------- ------------------------ 4.6/11.9 MB 5.7 MB/s eta 0:00:02
--------------- ------------------------ 4.7/11.9 MB 5.5 MB/s eta 0:00:02
----------------- ---------------------- 5.2/11.9 MB 5.3 MB/s eta 0:00:02
------------------ --------------------- 5.4/11.9 MB 5.1 MB/s eta 0:00:02
-------------------- ------------------- 6.2/11.9 MB 5.6 MB/s eta 0:00:02
---------------------- ----------------- 6.8/11.9 MB 5.6 MB/s eta 0:00:01
------------------------ --------------- 7.1/11.9 MB 5.8 MB/s eta 0:00:01
------------------------ --------------- 7.4/11.9 MB 5.7 MB/s eta 0:00:01
------------------------- -------------- 7.6/11.9 MB 5.6 MB/s eta 0:00:01
--------------------------- ------------ 8.0/11.9 MB 5.6 MB/s eta 0:00:01
---------------------------- ----------- 8.4/11.9 MB 5.7 MB/s eta 0:00:01
------------------------------ --------- 9.0/11.9 MB 5.8 MB/s eta 0:00:01
-------------------------------- ------- 9.5/11.9 MB 5.9 MB/s eta 0:00:01
--------------------------------- ------ 9.8/11.9 MB 6.0 MB/s eta 0:00:01
---------------------------------- ----- 10.4/11.9 MB 6.4 MB/s eta 0:00:01
------------------------------------ --- 10.8/11.9 MB 6.8 MB/s eta 0:00:01
------------------------------------- -- 11.2/11.9 MB 7.0 MB/s eta 0:00:01
--------------------------------------- 11.6/11.9 MB 6.9 MB/s eta 0:00:01
--------------------------------------- 11.8/11.9 MB 7.0 MB/s eta 0:00:01
--------------------------------------- 11.8/11.9 MB 7.0 MB/s eta 0:00:01
---------------------------------------- 11.9/11.9 MB 6.4 MB/s eta 0:00:00
Preparing metadata (setup.py): started
Preparing metadata (setup.py): finished with status 'done'
Building wheels for collected packages: mysql.connector
Building wheel for mysql.connector (setup.py): started
Building wheel for mysql.connector (setup.py): finished with status 'done'
Created wheel for mysql.connector: filename=mysql_connector-2.2.9-cp311-cp311-wi
n_amd64.whl size=247958 sha256=7cb80c9a2740fd25dc6d73e14c769a1f045366bc132788cf320
6feca09ff8a69
Stored in directory: c:\users\asus\appdata\local\pip\cache\wheels\17\cd\ed\2d49e
9bac69cf09382e4c7cc20a2511202b48324b87db26019
Successfully built mysql.connector
Installing collected packages: mysql.connector
Successfully installed mysql.connector-2.2.9

In [68]: import mysql.connector

In [72]: conn = mysql.connector.connect(host='localhost',user='root',password='',database='w

---------------------------------------------------------------------------
ProgrammingError Traceback (most recent call last)
Cell In[72], line 1
----> 1 conn = mysql.connector.connect(host='localhost',user='root',password='',da
tabase='world')

File ~\anaconda3\Lib\site-packages\mysql\connector\__init__.py:179, in connect(*ar

gs, **kwargs)
177 return CMySQLConnection(*args, **kwargs)
178 else:
--> 179 return MySQLConnection(*args, **kwargs)

File ~\anaconda3\Lib\site-packages\mysql\connector\connection.py:95, in MySQLConne

ction.__init__(self, *args, **kwargs)
92 self._pool_config_version = None
94 if len(kwargs) > 0:
---> 95 self.connect(**kwargs)

File ~\anaconda3\Lib\site-packages\mysql\connector\abstracts.py:716, in MySQLConne

ctionAbstract.connect(self, **kwargs)
713 self.config(**kwargs)
715 self.disconnect()
--> 716 self._open_connection()
717 self._post_connection()

File ~\anaconda3\Lib\site-packages\mysql\connector\connection.py:208, in MySQLConn

ection._open_connection(self)
206 self._socket.open_connection()
207 self._do_handshake()
--> 208 self._do_auth(self._user, self._password,
209 self._database, self._client_flags, self._charset_id,
210 self._ssl)
211 self.set_converter_class(self._converter_class)
212 if self._client_flags & ClientFlag.COMPRESS:

File ~\anaconda3\Lib\site-packages\mysql\connector\connection.py:144, in MySQLConn

ection._do_auth(self, username, password, database, client_flags, charset, ssl_opt
ions)
137 packet = self._protocol.make_auth(
138 handshake=self._handshake,
139 username=username, password=password, database=database,
140 charset=charset, client_flags=client_flags,
141 ssl_enabled=self._ssl_active,
142 auth_plugin=self._auth_plugin)
143 self._socket.send(packet)
--> 144 self._auth_switch_request(username, password)
146 if not (client_flags & ClientFlag.CONNECT_WITH_DB) and database:
147 self.cmd_init_db(database)

File ~\anaconda3\Lib\site-packages\mysql\connector\connection.py:173, in MySQLConn

ection._auth_switch_request(self, username, password)
171 packet = self._socket.recv()
172 if packet[4] != 1:
--> 173 return self._handle_ok(packet)
174 else:
175 auth_data = self._protocol.parse_auth_more_data(packet)

File ~\anaconda3\Lib\site-packages\mysql\connector\connection.py:331, in MySQLConn

ection._handle_ok(self, packet)
329 return ok_pkt
330 elif packet[4] == 255:
--> 331 raise errors.get_exception(packet)
332 raise errors.InterfaceError('Expected OK packet')
 ProgrammingError: 1045 (28000): Access denied for user 'root'@'localhost' (using p
assword: NO)

In [73]: df = pd.read_sql_query("SELECT * FROM countrylanguage",conn)

---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[73], line 1
----> 1 df = pd.read_sql_query("SELECT * FROM countrylanguage",conn)

NameError: name 'conn' is not defined

In [74]: df

Out[74]: enrollee_id city city_development_index gender relevent_experience enrolled_univers

Has relevent
0 8949 city_103 0.920 Male no_enrollme
experience

No relevent
1 29725 city_40 0.776 Male no_enrollme
experience

No relevent
2 11561 city_21 0.624 NaN Full time cou
experience

No relevent
3 33241 city_115 0.789 NaN N
experience

Has relevent
4 666 city_162 0.767 Male no_enrollme
experience

... ... ... ... ... ...

No relevent
19153 7386 city_173 0.878 Male no_enrollme
experience

Has relevent
19154 31398 city_103 0.920 Male no_enrollme
experience

Has relevent
19155 24576 city_103 0.920 Male no_enrollme
experience

Has relevent
19156 5756 city_65 0.802 Male no_enrollme
experience

No relevent
19157 23834 city_67 0.855 NaN no_enrollme
experience

19158 rows × 14 columns

In [ ]: