使用 FigureWidget ipywidgets 进行交互式数据分析¶
import datetime
import numpy as np
import pandas as pd
import plotly.graph_objects as go
from ipywidgets import widgets
NYC Flights Database¶
我们会申请查看 2013 年所有离开纽约的航班的延误情况。
df = pd.read_csv(
'https://media.githubusercontent.com/media/xinet-collections/test-dastsets/main/nycflights.csv')
df = df.drop(df.columns[[0]], axis=1)
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
<ipython-input-2-0d6ad44553ee> in <module>
----> 1 df = pd.read_csv(
2 'https://media.githubusercontent.com/media/xinet-collections/test-dastsets/main/nycflights.csv')
3 df = df.drop(df.columns[[0]], axis=1)
/usr/share/miniconda/lib/python3.8/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
312
313 return wrapper
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/readers.py in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)
584 kwds.update(kwds_defaults)
585
--> 586 return _read(filepath_or_buffer, kwds)
587
588
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/readers.py in _read(filepath_or_buffer, kwds)
480
481 # Create the parser.
--> 482 parser = TextFileReader(filepath_or_buffer, **kwds)
483
484 if chunksize or iterator:
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/readers.py in __init__(self, f, engine, **kwds)
809 self.options["has_index_names"] = kwds["has_index_names"]
810
--> 811 self._engine = self._make_engine(self.engine)
812
813 def close(self):
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/readers.py in _make_engine(self, engine)
1038 )
1039 # error: Too many arguments for "ParserBase"
-> 1040 return mapping[engine](self.f, **self.options) # type: ignore[call-arg]
1041
1042 def _failover_to_python(self):
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/c_parser_wrapper.py in __init__(self, src, **kwds)
49
50 # open handles
---> 51 self._open_handles(src, kwds)
52 assert self.handles is not None
53
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/parsers/base_parser.py in _open_handles(self, src, kwds)
220 Let the readers open IOHandles after they are done with their potential raises.
221 """
--> 222 self.handles = get_handle(
223 src,
224 "r",
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/common.py in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
606
607 # open URLs
--> 608 ioargs = _get_filepath_or_buffer(
609 path_or_buf,
610 encoding=encoding,
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/common.py in _get_filepath_or_buffer(filepath_or_buffer, encoding, compression, mode, storage_options)
309 # assuming storage_options is to be interpreted as headers
310 req_info = urllib.request.Request(filepath_or_buffer, headers=storage_options)
--> 311 with urlopen(req_info) as req:
312 content_encoding = req.headers.get("Content-Encoding", None)
313 if content_encoding == "gzip":
/usr/share/miniconda/lib/python3.8/site-packages/pandas/io/common.py in urlopen(*args, **kwargs)
209 import urllib.request
210
--> 211 return urllib.request.urlopen(*args, **kwargs)
212
213
/usr/share/miniconda/lib/python3.8/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
220 else:
221 opener = _opener
--> 222 return opener.open(url, data, timeout)
223
224 def install_opener(opener):
/usr/share/miniconda/lib/python3.8/urllib/request.py in open(self, fullurl, data, timeout)
529 for processor in self.process_response.get(protocol, []):
530 meth = getattr(processor, meth_name)
--> 531 response = meth(req, response)
532
533 return response
/usr/share/miniconda/lib/python3.8/urllib/request.py in http_response(self, request, response)
638 # request was successfully received, understood, and accepted.
639 if not (200 <= code < 300):
--> 640 response = self.parent.error(
641 'http', request, response, code, msg, hdrs)
642
/usr/share/miniconda/lib/python3.8/urllib/request.py in error(self, proto, *args)
567 if http_err:
568 args = (dict, 'default', 'http_error_default') + orig_args
--> 569 return self._call_chain(*args)
570
571 # XXX probably also want an abstract factory that knows when it makes
/usr/share/miniconda/lib/python3.8/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
500 for handler in handlers:
501 func = getattr(handler, meth_name)
--> 502 result = func(*args)
503 if result is not None:
504 return result
/usr/share/miniconda/lib/python3.8/urllib/request.py in http_error_default(self, req, fp, code, msg, hdrs)
647 class HTTPDefaultErrorHandler(BaseHandler):
648 def http_error_default(self, req, fp, code, msg, hdrs):
--> 649 raise HTTPError(req.full_url, code, msg, hdrs, fp)
650
651 class HTTPRedirectHandler(BaseHandler):
HTTPError: HTTP Error 404: Not Found
df.sample(3)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-3-b81a29911479> in <module>
----> 1 df.sample(3)
NameError: name 'df' is not defined
让我们获得所有 airlines 的集合，以便稍后在搜索框中输入正确的内容。
df['carrier'].unique()
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-4-8d832dfc27ce> in <module>
----> 1 df['carrier'].unique()
NameError: name 'df' is not defined
让我们来分配我们将在应用程序中使用的小部件。一般来说，所有这些小部件都将用于筛选数据集，从而实现可视化。
month = widgets.IntSlider(
value=1.0,
min=1.0,
max=12.0,
step=1.0,
description='Month:',
continuous_update=False
)
use_date = widgets.Checkbox(
description='Date: ',
value=True,
)
container = widgets.HBox(children=[use_date, month])
textbox = widgets.Dropdown(
description='Airline: ',
value='DL',
options=df['carrier'].unique().tolist()
)
origin = widgets.Dropdown(
options=list(df['origin'].unique()),
value='LGA',
description='Origin Airport:',
)
# Assign an empty figure widget with two traces
trace1 = go.Histogram(x=df['arr_delay'], opacity=0.75, name='Arrival Delays')
trace2 = go.Histogram(x=df['dep_delay'], opacity=0.75, name='Departure Delays')
g = go.FigureWidget(data=[trace1, trace2],
layout=go.Layout(
title=dict(
text='NYC FlightDatabase'
),
barmode='overlay'
))
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-5-ffdd5064d3eb> in <module>
18 description='Airline: ',
19 value='DL',
---> 20 options=df['carrier'].unique().tolist()
21 )
22
NameError: name 'df' is not defined
现在让我们编写一个函数来处理来自小部件的输入，并改变 graph 的状态。
def validate():
if origin.value in df['origin'].unique() and textbox.value in df['carrier'].unique():
return True
else:
return False
def response(change):
if validate():
if use_date.value:
filter_list = [i and j and k for i, j, k in
zip(df['month'] == month.value, df['carrier'] == textbox.value,
df['origin'] == origin.value)]
temp_df = df[filter_list]
else:
filter_list = [i and j for i, j in
zip(df['carrier'] == 'DL', df['origin'] == origin.value)]
temp_df = df[filter_list]
x1 = temp_df['arr_delay']
x2 = temp_df['dep_delay']
with g.batch_update():
g.data[0].x = x1
g.data[1].x = x2
g.layout.barmode = 'overlay'
g.layout.xaxis.title = 'Delay in Minutes'
g.layout.yaxis.title = 'Number of Delays'
origin.observe(response, names="value")
textbox.observe(response, names="value")
month.observe(response, names="value")
use_date.observe(response, names="value")
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-6-87aeb724f65f> in <module>
28
29
---> 30 origin.observe(response, names="value")
31 textbox.observe(response, names="value")
32 month.observe(response, names="value")
NameError: name 'origin' is not defined
是时候试试这个应用了！！
container2 = widgets.HBox([origin, textbox])
widgets.VBox([container,
container2,
g])
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-7-ca1441aa06fd> in <module>
----> 1 container2 = widgets.HBox([origin, textbox])
2 widgets.VBox([container,
3 container2,
4 g])
NameError: name 'origin' is not defined
