import pandas as pd
iris = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=None,
names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'class'])
type(iris)
iris.head(10)
sepal_lengthfloat64
4.4 - 5.4
sepal_widthfloat64
2.9 - 3.9
0
5.1
3.5
1
4.9
3
2
4.7
3.2
3
4.6
3.1
4
5
3.6
5
5.4
3.9
6
4.6
3.4
7
5
3.4
8
4.4
2.9
9
4.9
3.1
iris.tail(10)
sepal_lengthfloat64
5.8 - 6.9
sepal_widthfloat64
2.5 - 3.4
140
6.7
3.1
141
6.9
3.1
142
5.8
2.7
143
6.8
3.2
144
6.7
3.3
145
6.7
3
146
6.3
2.5
147
6.5
3
148
6.2
3.4
149
5.9
3
This chart is empty
Chart was probably not set up properly in the notebook
iris.columns
iris['class']
type(iris['class'])
iris.dtypes
iris.shape
iris.info
import pandas as pd
values = {'dates': ['20210305','20210316','20210328'],
'status': ['Opened','Opened','Closed']
}
demo = pd.DataFrame(values)
demo
datesobject
statusobject
0
20210305
Opened
1
20210316
Opened
2
20210328
Closed
demo['dates'] = pd.to_datetime(demo['dates'], format='%Y%m%d')
demo
datesdatetime64[ns]
statusobject
0
2021-03-05T00:00:00.000000
Opened
1
2021-03-16T00:00:00.000000
Opened
2
2021-03-28T00:00:00.000000
Closed
demo.to_csv('demo_df.csv')
print(iris.index)
print(iris.columns)
RangeIndex(start=0, stop=150, step=1)
Index(['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'class'], dtype='object')
iris.head()
sepal_lengthfloat64
sepal_widthfloat64
0
5.1
3.5
1
4.9
3
2
4.7
3.2
3
4.6
3.1
4
5
3.6
iris['sepal_width'][4]
iris['sepal_width'][0:4]
iris[['petal_width','sepal_width']][0:4]
petal_widthfloat64
sepal_widthfloat64
0
0.2
3.5
1
0.2
3
2
0.2
3.2
3
0.2
3.1
iris['sepal_width'][range(4)]
iris.loc[4,'sepal_width']
iris.loc[0:4,'sepal_width'] #inclusive
iris.loc[range(4),['petal_width','sepal_width']]
petal_widthfloat64
sepal_widthfloat64
0
0.2
3.5
1
0.2
3
2
0.2
3.2
3
0.2
3.1
iris.iloc[4,1]
iris.iloc[0:4,1]
iris.iloc[range(4),[3,1]]
petal_widthfloat64
sepal_widthfloat64
0
0.2
3.5
1
0.2
3
2
0.2
3.2
3
0.2
3.1
iris.loc[:,lambda df: ['petal_length','sepal_length']]
petal_lengthfloat64
1.0 - 6.9
sepal_lengthfloat64
4.3 - 7.9
0
1.4
5.1
1
1.4
4.9
2
1.3
4.7
3
1.5
4.6
4
1.4
5
5
1.7
5.4
6
1.4
4.6
7
1.5
5
8
1.4
4.4
9
1.5
4.9
iris.loc[lambda iris: iris['sepal_width'] > 3.5, :]
sepal_lengthfloat64
4.6 - 7.9
sepal_widthfloat64
3.6 - 4.4
4
5
3.6
5
5.4
3.9
10
5.4
3.7
14
5.8
4
15
5.7
4.4
16
5.4
3.9
18
5.7
3.8
19
5.1
3.8
21
5.1
3.7
22
4.6
3.6
help(pd.read_csv)
Help on function read_csv in module pandas.io.parsers:
read_csv(filepath_or_buffer: Union[ForwardRef('PathLike[str]'), str, IO[~T], io.RawIOBase, io.BufferedIOBase, io.TextIOBase, _io.TextIOWrapper, mmap.mmap], sep=<object object at 0x7f4ea874d650>, delimiter=None, header='infer', names=None, index_col=None, usecols=None, squeeze=False, prefix=None, 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=False, 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: str = '.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, dialect=None, error_bad_lines=True, warn_bad_lines=True, delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None, storage_options: Union[Dict[str, Any], NoneType] = None)
Read a comma-separated values (csv) file into DataFrame.
Also supports optionally iterating or breaking of the file
into chunks.
Additional help can be found in the online docs for
`IO Tools <https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html>`_.
Parameters
----------
filepath_or_buffer : str, path object or file-like object
Any valid string path is acceptable. The string could be a URL. Valid
URL schemes include http, ftp, s3, gs, and file. For file URLs, a host is
expected. A local file could be: file://localhost/path/to/table.csv.
If you want to pass in a path object, pandas accepts any ``os.PathLike``.
By file-like object, we refer to objects with a ``read()`` method, such as
a file handle (e.g. via builtin ``open`` function) or ``StringIO``.
sep : str, default ','
Delimiter to use. If sep is None, the C engine cannot automatically detect
the separator, but the Python parsing engine can, meaning the latter will
be used and automatically detect the separator by Python's builtin sniffer
tool, ``csv.Sniffer``. In addition, separators longer than 1 character and
different from ``'\s+'`` will be interpreted as regular expressions and
will also force the use of the Python parsing engine. Note that regex
delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``.
delimiter : str, default ``None``
Alias for sep.
header : int, list of int, default 'infer'
Row number(s) to use as the column names, and the start of the
data. Default behavior is to infer the column names: if no names
are passed the behavior is identical to ``header=0`` and column
names are inferred from the first line of the file, if column
names are passed explicitly then the behavior is identical to
``header=None``. Explicitly pass ``header=0`` to be able to
replace existing names. The header can be a list of integers that
specify row locations for a multi-index on the columns
e.g. [0,1,3]. Intervening rows that are not specified will be
skipped (e.g. 2 in this example is skipped). Note that this
parameter ignores commented lines and empty lines if
``skip_blank_lines=True``, so ``header=0`` denotes the first line of
data rather than the first line of the file.
names : array-like, optional
List of column names to use. If the file contains a header row,
then you should explicitly pass ``header=0`` to override the column names.
Duplicates in this list are not allowed.
index_col : int, str, sequence of int / str, or False, default ``None``
Column(s) to use as the row labels of the ``DataFrame``, either given as
string name or column index. If a sequence of int / str is given, a
MultiIndex is used.
Note: ``index_col=False`` can be used to force pandas to *not* use the first
column as the index, e.g. when you have a malformed file with delimiters at
the end of each line.
usecols : list-like or callable, optional
Return a subset of the columns. If list-like, all elements must either
be positional (i.e. integer indices into the document columns) or strings
that correspond to column names provided either by the user in `names` or
inferred from the document header row(s). For example, a valid list-like
`usecols` parameter would be ``[0, 1, 2]`` or ``['foo', 'bar', 'baz']``.
Element order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``.
To instantiate a DataFrame from ``data`` with element order preserved use
``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns
in ``['foo', 'bar']`` order or
``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]``
for ``['bar', 'foo']`` order.
If callable, the callable function will be evaluated against the column
names, returning names where the callable function evaluates to True. An
example of a valid callable argument would be ``lambda x: x.upper() in
['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster
parsing time and lower memory usage.
squeeze : bool, default False
If the parsed data only contains one column then return a Series.
prefix : str, optional
Prefix to add to column numbers when no header, e.g. 'X' for X0, X1, ...
mangle_dupe_cols : bool, default True
Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than
'X'...'X'. Passing in False will cause data to be overwritten if there
are duplicate names in the columns.
dtype : Type name or dict of column -> type, optional
Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32,
'c': 'Int64'}
Use `str` or `object` together with suitable `na_values` settings
to preserve and not interpret dtype.
If converters are specified, they will be applied INSTEAD
of dtype conversion.
engine : {'c', 'python'}, optional
Parser engine to use. The C engine is faster while the python engine is
currently more feature-complete.
converters : dict, optional
Dict of functions for converting values in certain columns. Keys can either
be integers or column labels.
true_values : list, optional
Values to consider as True.
false_values : list, optional
Values to consider as False.
skipinitialspace : bool, default False
Skip spaces after delimiter.
skiprows : list-like, int or callable, optional
Line numbers to skip (0-indexed) or number of lines to skip (int)
at the start of the file.
If callable, the callable function will be evaluated against the row
indices, returning True if the row should be skipped and False otherwise.
An example of a valid callable argument would be ``lambda x: x in [0, 2]``.
skipfooter : int, default 0
Number of lines at bottom of file to skip (Unsupported with engine='c').
nrows : int, optional
Number of rows of file to read. Useful for reading pieces of large files.
na_values : scalar, str, list-like, or dict, optional
Additional strings to recognize as NA/NaN. If dict passed, specific
per-column NA values. By default the following values are interpreted as
NaN: '', '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN', '-NaN', '-nan',
'1.#IND', '1.#QNAN', '<NA>', 'N/A', 'NA', 'NULL', 'NaN', 'n/a',
'nan', 'null'.
keep_default_na : bool, default True
Whether or not to include the default NaN values when parsing the data.
Depending on whether `na_values` is passed in, the behavior is as follows:
* If `keep_default_na` is True, and `na_values` are specified, `na_values`
is appended to the default NaN values used for parsing.
* If `keep_default_na` is True, and `na_values` are not specified, only
the default NaN values are used for parsing.
* If `keep_default_na` is False, and `na_values` are specified, only
the NaN values specified `na_values` are used for parsing.
* If `keep_default_na` is False, and `na_values` are not specified, no
strings will be parsed as NaN.
Note that if `na_filter` is passed in as False, the `keep_default_na` and
`na_values` parameters will be ignored.
na_filter : bool, default True
Detect missing value markers (empty strings and the value of na_values). In
data without any NAs, passing na_filter=False can improve the performance
of reading a large file.
verbose : bool, default False
Indicate number of NA values placed in non-numeric columns.
skip_blank_lines : bool, default True
If True, skip over blank lines rather than interpreting as NaN values.
parse_dates : bool or list of int or names or list of lists or dict, default False
The behavior is as follows:
* boolean. If True -> try parsing the index.
* list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3
each as a separate date column.
* list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as
a single date column.
* dict, e.g. {'foo' : [1, 3]} -> parse columns 1, 3 as date and call
result 'foo'
If a column or index cannot be represented as an array of datetimes,
say because of an unparsable value or a mixture of timezones, the column
or index will be returned unaltered as an object data type. For
non-standard datetime parsing, use ``pd.to_datetime`` after
``pd.read_csv``. To parse an index or column with a mixture of timezones,
specify ``date_parser`` to be a partially-applied
:func:`pandas.to_datetime` with ``utc=True``. See
:ref:`io.csv.mixed_timezones` for more.
Note: A fast-path exists for iso8601-formatted dates.
infer_datetime_format : bool, default False
If True and `parse_dates` is enabled, pandas will attempt to infer the
format of the datetime strings in the columns, and if it can be inferred,
switch to a faster method of parsing them. In some cases this can increase
the parsing speed by 5-10x.
keep_date_col : bool, default False
If True and `parse_dates` specifies combining multiple columns then
keep the original columns.
date_parser : function, optional
Function to use for converting a sequence of string columns to an array of
datetime instances. The default uses ``dateutil.parser.parser`` to do the
conversion. Pandas will try to call `date_parser` in three different ways,
advancing to the next if an exception occurs: 1) Pass one or more arrays
(as defined by `parse_dates`) as arguments; 2) concatenate (row-wise) the
string values from the columns defined by `parse_dates` into a single array
and pass that; and 3) call `date_parser` once for each row using one or
more strings (corresponding to the columns defined by `parse_dates`) as
arguments.
dayfirst : bool, default False
DD/MM format dates, international and European format.
cache_dates : bool, default True
If True, use a cache of unique, converted dates to apply the datetime
conversion. May produce significant speed-up when parsing duplicate
date strings, especially ones with timezone offsets.
.. versionadded:: 0.25.0
iterator : bool, default False
Return TextFileReader object for iteration or getting chunks with
``get_chunk()``.
.. versionchanged:: 1.2
``TextFileReader`` is a context manager.
chunksize : int, optional
Return TextFileReader object for iteration.
See the `IO Tools docs
<https://pandas.pydata.org/pandas-docs/stable/io.html#io-chunking>`_
for more information on ``iterator`` and ``chunksize``.
.. versionchanged:: 1.2
``TextFileReader`` is a context manager.
compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'
For on-the-fly decompression of on-disk data. If 'infer' and
`filepath_or_buffer` is path-like, then detect compression from the
following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no
decompression). If using 'zip', the ZIP file must contain only one data
file to be read in. Set to None for no decompression.
thousands : str, optional
Thousands separator.
decimal : str, default '.'
Character to recognize as decimal point (e.g. use ',' for European data).
lineterminator : str (length 1), optional
Character to break file into lines. Only valid with C parser.
quotechar : str (length 1), optional
The character used to denote the start and end of a quoted item. Quoted
items can include the delimiter and it will be ignored.
quoting : int or csv.QUOTE_* instance, default 0
Control field quoting behavior per ``csv.QUOTE_*`` constants. Use one of
QUOTE_MINIMAL (0), QUOTE_ALL (1), QUOTE_NONNUMERIC (2) or QUOTE_NONE (3).
doublequote : bool, default ``True``
When quotechar is specified and quoting is not ``QUOTE_NONE``, indicate
whether or not to interpret two consecutive quotechar elements INSIDE a
field as a single ``quotechar`` element.
escapechar : str (length 1), optional
One-character string used to escape other characters.
comment : str, optional
Indicates remainder of line should not be parsed. If found at the beginning
of a line, the line will be ignored altogether. This parameter must be a
single character. Like empty lines (as long as ``skip_blank_lines=True``),
fully commented lines are ignored by the parameter `header` but not by
`skiprows`. For example, if ``comment='#'``, parsing
``#empty\na,b,c\n1,2,3`` with ``header=0`` will result in 'a,b,c' being
treated as the header.
encoding : str, optional
Encoding to use for UTF when reading/writing (ex. 'utf-8'). `List of Python
standard encodings
<https://docs.python.org/3/library/codecs.html#standard-encodings>`_ .
.. versionchanged:: 1.2
When ``encoding`` is ``None``, ``errors="replace"`` is passed to
``open()``. Otherwise, ``errors="strict"`` is passed to ``open()``.
This behavior was previously only the case for ``engine="python"``.
dialect : str or csv.Dialect, optional
If provided, this parameter will override values (default or not) for the
following parameters: `delimiter`, `doublequote`, `escapechar`,
`skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to
override values, a ParserWarning will be issued. See csv.Dialect
documentation for more details.
error_bad_lines : bool, default True
Lines with too many fields (e.g. a csv line with too many commas) will by
default cause an exception to be raised, and no DataFrame will be returned.
If False, then these "bad lines" will dropped from the DataFrame that is
returned.
warn_bad_lines : bool, default True
If error_bad_lines is False, and warn_bad_lines is True, a warning for each
"bad line" will be output.
delim_whitespace : bool, default False
Specifies whether or not whitespace (e.g. ``' '`` or ``' '``) will be
used as the sep. Equivalent to setting ``sep='\s+'``. If this option
is set to True, nothing should be passed in for the ``delimiter``
parameter.
low_memory : bool, default True
Internally process the file in chunks, resulting in lower memory use
while parsing, but possibly mixed type inference. To ensure no mixed
types either set False, or specify the type with the `dtype` parameter.
Note that the entire file is read into a single DataFrame regardless,
use the `chunksize` or `iterator` parameter to return the data in chunks.
(Only valid with C parser).
memory_map : bool, default False
If a filepath is provided for `filepath_or_buffer`, map the file object
directly onto memory and access the data directly from there. Using this
option can improve performance because there is no longer any I/O overhead.
float_precision : str, optional
Specifies which converter the C engine should use for floating-point
values. The options are ``None`` or 'high' for the ordinary converter,
'legacy' for the original lower precision pandas converter, and
'round_trip' for the round-trip converter.
.. versionchanged:: 1.2
storage_options : dict, optional
Extra options that make sense for a particular storage connection, e.g.
host, port, username, password, etc., if using a URL that will
be parsed by ``fsspec``, e.g., starting "s3://", "gcs://". An error
will be raised if providing this argument with a non-fsspec URL.
See the fsspec and backend storage implementation docs for the set of
allowed keys and values.
.. versionadded:: 1.2
Returns
-------
DataFrame or TextParser
A comma-separated values (csv) file is returned as two-dimensional
data structure with labeled axes.
See Also
--------
DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file.
read_csv : Read a comma-separated values (csv) file into DataFrame.
read_fwf : Read a table of fixed-width formatted lines into DataFrame.
Examples
--------
>>> pd.read_csv('data.csv') # doctest: +SKIP
import pandas as pd
# How to read CSV file from GitHub using pandas
# https://stackoverflow.com/questions/55240330/how-to-read-csv-file-from-github-using-pandas
url = 'https://raw.githubusercontent.com/pairote-sat/SCMA248/main/demo_df'
df1 = pd.read_csv(url)
print(df1.head())
df1.columns
Unnamed: 0 dates status
0 0 5032021 Opened
1 1 16032021 Opened
2 2 28032021 Closed
## Uncomment these commands if the CSV dateset is stored locally.
# df1 = pd.read_csv('/Users/Kaemyuijang/SCMA248/demo_df.csv')
# print(df1.head())
# df1.columns
df1 = pd.read_csv(url, index_col = 0)
df1.head()
datesint64
statusobject
0
5032021
Opened
1
16032021
Opened
2
28032021
Closed
# df2 = pd.read_csv('/Users/Kaemyuijang/SCMA248/demo_df.csv', index_col = 0, parse_dates = ['dates'])
# print(df2.head())
# df2.dtypes
df2 = pd.read_csv(url, index_col = 0, parse_dates = ['dates'])
print(df2)
df2.dtypes
dates status
0 05032021 Opened
1 16032021 Opened
2 28032021 Closed
df2['dates'] = pd.to_datetime(df2['dates'], format='%d%m%Y')
print(df2)
df2.dtypes
dates status
0 2021-03-05 Opened
1 2021-03-16 Opened
2 2021-03-28 Closed
url = 'https://raw.githubusercontent.com/pairote-sat/SCMA248/main/property_data.csv'
df = pd.read_csv(url, index_col = 0)
df
ST_NUMfloat64
104.0 - 215.0
ST_NAMEobject
Sukhumvit33.3%
Silom22.2%
3 others44.4%
10101
104
Khao San
10102
197
Silom
10103
nan
Silom
10104
201
Sukhumvit
nan
203
Sukhumvit
10106
207
Sukhumvit
10107
nan
Thonglor
10108
213
Rama 1
10109
215
Rama 1
rowindex = df.index
type(rowindex)
rowindex = df.index.tolist()
rowindex[4] = 10105.0
rowindex = [int(i) for i in rowindex]
df.index = rowindex
print(df.loc[:,'ST_NUM'])
10101 104.0
10102 197.0
10103 NaN
10104 201.0
10105 203.0
10106 207.0
10107 NaN
10108 213.0
10109 215.0
Name: ST_NUM, dtype: float64
df = pd.read_csv(url, index_col = 0)
df
import numpy as np
rowindex = df.index.to_numpy()
rowindex[4] = 10105.0
df.index = rowindex.astype(int)
print(df.loc[:,'ST_NUM'])
10101 104.0
10102 197.0
10103 NaN
10104 201.0
10105 203.0
10106 207.0
10107 NaN
10108 213.0
10109 215.0
Name: ST_NUM, dtype: float64
df['ST_NUM'].isnull()
df['NUM_BEDROOMS']
# Making a list of missing value types
missing_values = ["na", "--"]
df = pd.read_csv(url, index_col = 0, na_values = missing_values)
df
ST_NUMfloat64
104.0 - 215.0
ST_NAMEobject
Sukhumvit33.3%
Silom22.2%
3 others44.4%
10101
104
Khao San
10102
197
Silom
10103
nan
Silom
10104
201
Sukhumvit
nan
203
Sukhumvit
10106
207
Sukhumvit
10107
nan
Thonglor
10108
213
Rama 1
10109
215
Rama 1
df['OWN_OCCUPIED']
df = pd.read_csv(url, index_col = 0)
df
import numpy as np
rowindex = df.index.to_numpy()
rowindex[4] = 10105.0
df.index = rowindex.astype(int)
df
ST_NUMfloat64
104.0 - 215.0
ST_NAMEobject
Sukhumvit33.3%
Silom22.2%
3 others44.4%
10101
104
Khao San
10102
197
Silom
10103
nan
Silom
10104
201
Sukhumvit
10105
203
Sukhumvit
10106
207
Sukhumvit
10107
nan
Thonglor
10108
213
Rama 1
10109
215
Rama 1
# Detecting numbers
cnt=10101
for row in df['OWN_OCCUPIED']:
try:
int(row)
df.loc[cnt, 'OWN_OCCUPIED']=np.nan
except ValueError:
pass
cnt+=1
df['OWN_OCCUPIED']