Develop Reference

How to create a regplot in Pyspark - tough time with sparse vector

I am using a Colab Notebook and doing a linear regression in Pyspark.
I completed the whole regression with no problems. However, we were asked to add a regression plot, and that's where I am stuck.
I had multiple features in my dataset which I clubbed into one column using the feature assembler. Here is what my predicted dataset looks like:
I now want to create something like this:
And I am using the following code:
import chart_studio.plotly as py
import plotly.graph_objects as go
x = mdata.toPandas()['Independent_Features'].values.tolist()
y = mdata.toPandas()['MonthlyCharges'].values.tolist()
y_pred=mdata.toPandas()['prediction'].values.tolist()
fig = go.Figure()
fig.add_trace(
go.Scatter(
x=x,
y=y,
mode='markers',
name='Original_Data',
))
fig.add_trace(
go.Scatter(
x=x,
y=y_pred,
name='Predicted'
))
fig.update_layout(
title="Linear Regression",
xaxis_title="Independent Features",
yaxis_title="Monthly Charges",
font=dict(
family="Courier New, monospace",
size=18,
color="#7f7f7f"
)
)
fig.show()
But I am getting this error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-45-cb270db7e5d4> in <module>()
30
31
---> 32 fig.show()
11 frames
/usr/local/lib/python3.7/dist-packages/plotly/basedatatypes.py in show(self, *args, **kwargs)
3396 import plotly.io as pio
3397
-> 3398 return pio.show(self, *args, **kwargs)
3399
3400 def to_json(self, *args, **kwargs):
/usr/local/lib/python3.7/dist-packages/plotly/io/_renderers.py in show(fig, renderer, validate, **kwargs)
387
388 # Mimetype renderers
--> 389 bundle = renderers._build_mime_bundle(fig_dict, renderers_string=renderer, **kwargs)
390 if bundle:
391 if not ipython_display:
/usr/local/lib/python3.7/dist-packages/plotly/io/_renderers.py in _build_mime_bundle(self, fig_dict, renderers_string, **kwargs)
295 setattr(renderer, k, v)
296
--> 297 bundle.update(renderer.to_mimebundle(fig_dict))
298
299 return bundle
/usr/local/lib/python3.7/dist-packages/plotly/io/_base_renderers.py in to_mimebundle(self, fig_dict)
389 default_width="100%",
390 default_height=525,
--> 391 validate=False,
392 )
393
/usr/local/lib/python3.7/dist-packages/plotly/io/_html.py in to_html(fig, config, auto_play, include_plotlyjs, include_mathjax, post_script, full_html, animation_opts, default_width, default_height, validate, div_id)
144
145 # ## Serialize figure ##
--> 146 jdata = to_json_plotly(fig_dict.get("data", []))
147 jlayout = to_json_plotly(fig_dict.get("layout", {}))
148
/usr/local/lib/python3.7/dist-packages/plotly/io/_json.py in to_json_plotly(plotly_object, pretty, engine)
122 from _plotly_utils.utils import PlotlyJSONEncoder
123
--> 124 return json.dumps(plotly_object, cls=PlotlyJSONEncoder, **opts)
125 elif engine == "orjson":
126 JsonConfig.validate_orjson()
/usr/lib/python3.7/json/__init__.py in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
236 check_circular=check_circular, allow_nan=allow_nan, indent=indent,
237 separators=separators, default=default, sort_keys=sort_keys,
--> 238 **kw).encode(obj)
239
240
/usr/local/lib/python3.7/dist-packages/_plotly_utils/utils.py in encode(self, o)
57 """
58 # this will raise errors in a normal-expected way
---> 59 encoded_o = super(PlotlyJSONEncoder, self).encode(o)
60 # Brute force guessing whether NaN or Infinity values are in the string
61 # We catch false positive cases (e.g. strings such as titles, labels etc.)
/usr/lib/python3.7/json/encoder.py in encode(self, o)
197 # exceptions aren't as detailed. The list call should be roughly
198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
200 if not isinstance(chunks, (list, tuple)):
201 chunks = list(chunks)
/usr/lib/python3.7/json/encoder.py in iterencode(self, o, _one_shot)
255 self.key_separator, self.item_separator, self.sort_keys,
256 self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)
258
259 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
/usr/local/lib/python3.7/dist-packages/_plotly_utils/utils.py in default(self, obj)
134 except NotEncodable:
135 pass
--> 136 return _json.JSONEncoder.default(self, obj)
137
138 #staticmethod
/usr/lib/python3.7/json/encoder.py in default(self, o)
177
178 """
--> 179 raise TypeError(f'Object of type {o.__class__.__name__} '
180 f'is not JSON serializable')
181
TypeError: Object of type SparseVector is not JSON serializable
Here is a link to the notebook: https://colab.research.google.com/drive/1NLibPkZgOE_w7dVTerAF4nUQiPXW_o06?usp=sharing
I saw it mentioned SparseVector, so I tried to convert it to a DenseVector, but that just wouldn't work, tried multiple commands, but nothing helps.

custom function for scatterplot in bokeh not running

dataset i am working on:
https://www.kaggle.com/code/gauravsahani/housing-in-london-for-beginners/data
i am using bokeh and have produced the following scatter plot
source=ColumnDataSource(data=dict(df,av=df.average_price,cr=df.no_of_crimes,ar=df.area))
p=figure(sizing_mode='stretch_width',toolbar_location=None,height=500,
x_axis_label='Average Salary',y_axis_label='crime rate')
p.xaxis.formatter = BasicTickFormatter(use_scientific=False)
p.add_layout(Legend(), 'right')
p.scatter(x='av',y='cr',source=source,size=9,alpha=0.4,legend_field='area',fill_color=factor_cmap('area',palette=magma(34),factors=df.area.unique()))
p.xgrid.grid_line_color=None
p.legend.label_text_font_size='12px'
p.legend.padding=4
p.legend.orientation='vertical'
p.legend.spacing=-7
p.add_tools(HoverTool(tooltips=[('Area','#ar')]))
show(p)
I am trying to produce a custom function for reusability which is the following:
source=ColumnDataSource(data=dict(df,av=df.average_price,
cr=df.no_of_crimes,
ar=df.area))
tooltips=[('Area','#ar')]
def scatter(source,x,y,xlabel=None,ylabel=None,size=None,alpha=None,legend_field=None,fill_color=None):
p=figure(sizing_mode='stretch_width',
toolbar_location=None,
height=500,
x_axis_label=xlabel,
y_axis_label=ylabel)
p.xgrid.grid_line_color=None
p.xaxis.formatter = BasicTickFormatter(use_scientific=False)
p.legend.label_text_font_size='12px'
p.legend.padding=4
p.legend.orientation='vertical'
p.legend.spacing=-7
p.scatter(source=source,x=x,y=y,size=size,alpha=alpha,legend_field=legend_field,fill_color=fill_color)
return p
p=scatter(source,x='av',y='cr')
show(p)
however I keep getting an error and I cant seem to figure out why since both my x and y columns are numerical values and already run successfuly when not working with a function. the error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [234], in <cell line: 24>()
20 p.scatter(source=source,x=x,y=y,size=size,alpha=alpha,legend_field=legend_field,fill_color=fill_color)
22 return p
---> 24 p=scatter(source,x='av',y='cr')
26 show(p)
Input In [234], in scatter(source, x, y, xlabel, ylabel, size, alpha, legend_field, fill_color)
17 p.legend.orientation='vertical'
18 p.legend.spacing=-7
---> 20 p.scatter(source=source,x=x,y=y,size=size,alpha=alpha,legend_field=legend_field,fill_color=fill_color)
22 return p
File ~\Anaconda3\lib\site-packages\bokeh\plotting\glyph_api.py:962, in GlyphAPI.scatter(self, *args, **kwargs)
960 return self.circle(*args, **kwargs)
961 else:
--> 962 return self._scatter(*args, marker=marker_type, **kwargs)
File ~\Anaconda3\lib\site-packages\bokeh\plotting\_decorators.py:86, in glyph_method.<locals>.decorator.<locals>.wrapped(self, *args, **kwargs)
84 if self.coordinates is not None:
85 kwargs.setdefault("coordinates", self.coordinates)
---> 86 return create_renderer(glyphclass, self.plot, **kwargs)
File ~\Anaconda3\lib\site-packages\bokeh\plotting\_renderer.py:116, in create_renderer(glyphclass, plot, **kwargs)
113 # handle the mute glyph, we always set one
114 muted_visuals = pop_visuals(glyphclass, kwargs, prefix='muted_', defaults=glyph_visuals, override_defaults={'alpha':0.2})
--> 116 glyph = make_glyph(glyphclass, kwargs, glyph_visuals)
117 nonselection_glyph = make_glyph(glyphclass, kwargs, nonselection_visuals)
118 selection_glyph = make_glyph(glyphclass, kwargs, selection_visuals)
File ~\Anaconda3\lib\site-packages\bokeh\plotting\_renderer.py:145, in make_glyph(glyphclass, kws, extra)
143 kws = kws.copy()
144 kws.update(extra)
--> 145 return glyphclass(**kws)
File ~\Anaconda3\lib\site-packages\bokeh\model\model.py:128, in Model.__init__(self, **kwargs)
121 def __init__(self, **kwargs: Any) -> None:
122
123 # "id" is popped from **kw in __new__, so in an ideal world I don't
124 # think it should be here too. But Python has subtle behavior here, so
125 # it is necessary
126 kwargs.pop("id", None)
--> 128 super().__init__(**kwargs)
129 default_theme.apply_to_model(self)
File ~\Anaconda3\lib\site-packages\bokeh\core\has_props.py:206, in HasProps.__init__(self, **properties)
203 self._unstable_themed_values = {}
205 for name, value in properties.items():
--> 206 setattr(self, name, value)
208 self._initialized = True
File ~\Anaconda3\lib\site-packages\bokeh\core\has_props.py:230, in HasProps.__setattr__(self, name, value)
228 properties = self.properties(_with_props=True)
229 if name in properties:
--> 230 return super().__setattr__(name, value)
232 descriptor = getattr(self.__class__, name, None)
233 if isinstance(descriptor, property): # Python property
File ~\Anaconda3\lib\site-packages\bokeh\core\property\descriptors.py:283, in PropertyDescriptor.__set__(self, obj, value, setter)
280 class_name = obj.__class__.__name__
281 raise RuntimeError(f"{class_name}.{self.name} is a readonly property")
--> 283 value = self.property.prepare_value(obj, self.name, value)
284 old = self._get(obj)
285 self._set(obj, old, value, setter=setter)
File ~\Anaconda3\lib\site-packages\bokeh\core\property\dataspec.py:515, in SizeSpec.prepare_value(self, cls, name, value)
513 except TypeError:
514 pass
--> 515 return super().prepare_value(cls, name, value)
File ~\Anaconda3\lib\site-packages\bokeh\core\property\bases.py:365, in Property.prepare_value(self, owner, name, value, hint)
363 else:
364 obj_repr = owner if isinstance(owner, HasProps) else owner.__name__
--> 365 raise ValueError(f"failed to validate {obj_repr}.{name}: {error}")
367 if isinstance(owner, HasProps):
368 obj = owner
ValueError: failed to validate Scatter(id='40569', ...).size: expected an element of either String, Dict(Enum('expr', 'field', 'value', 'transform'), Either(String, Instance(Transform), Instance(Expression), Float)) or Float, got None
any help would be great

def scatter(source,x,y,xlabel=None,ylabel=None,size=5,alpha=1,legend_field=str(None),fill_color=None):
p=figure(sizing_mode='stretch_width',
toolbar_location=None,
height=500,
x_axis_label=xlabel,
y_axis_label=ylabel)
p.xgrid.grid_line_color=None
p.xaxis.formatter = BasicTickFormatter(use_scientific=False)
p.legend.label_text_font_size='12px'
p.legend.padding=4
p.legend.orientation='vertical'
p.legend.spacing=-7
if legend_field == str(None):
p.scatter(source=source,x=x,y=y,size=size,alpha=alpha,fill_color=fill_color)
else:
p.scatter(source=source,x=x,y=y,size=size,alpha=alpha,legend_field=legend_field,fill_color=fill_color)
return p

seaborn lmplot logistic raises AttributeError: module 'pandas' has no attribute 'Panel'

I am using the code below that I took from the Seaborn documentation as it is. Running this code results in an error.
AttributeError: module 'pandas' has no attribute 'Panel'
I am wondering if there is a way around this problem without reverting to a previous version of Pandas. Can anyone help?
tips = sns.load_dataset("tips")
tips["big_tip"] = (tips.tip / tips.total_bill) > .15
sns.lmplot(x="total_bill", y="big_tip", data=tips,
logistic=True, y_jitter=.03);
The version info as well as the complete error message are as follows:
pandas : 1.3.5
seaborn: '0.11.2'
--------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-4-2a96c34ef86c> in <module>
2 tips["big_tip"] = (tips.tip / tips.total_bill) > .15
3 sns.lmplot(x="total_bill", y="big_tip", data=tips,
----> 4 logistic=True, y_jitter=.03);
~/anaconda3/lib/python3.7/site-packages/seaborn/_decorators.py in inner_f(*args, **kwargs)
44 )
45 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 46 return f(**kwargs)
47 return inner_f
48
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in lmplot(x, y, data, hue, col, row, palette, col_wrap, height, aspect, markers, sharex, sharey, hue_order, col_order, row_order, legend, legend_out, x_estimator, x_bins, x_ci, scatter, fit_reg, ci, n_boot, units, seed, order, logistic, lowess, robust, logx, x_partial, y_partial, truncate, x_jitter, y_jitter, scatter_kws, line_kws, facet_kws, size)
643 scatter_kws=scatter_kws, line_kws=line_kws,
644 )
--> 645 facets.map_dataframe(regplot, x=x, y=y, **regplot_kws)
646 facets.set_axis_labels(x, y)
647
~/anaconda3/lib/python3.7/site-packages/seaborn/axisgrid.py in map_dataframe(self, func, *args, **kwargs)
775
776 # Draw the plot
--> 777 self._facet_plot(func, ax, args, kwargs)
778
779 # For axis labels, prefer to use positional args for backcompat
~/anaconda3/lib/python3.7/site-packages/seaborn/axisgrid.py in _facet_plot(self, func, ax, plot_args, plot_kwargs)
804 plot_args = []
805 plot_kwargs["ax"] = ax
--> 806 func(*plot_args, **plot_kwargs)
807
808 # Sort out the supporting information
~/anaconda3/lib/python3.7/site-packages/seaborn/_decorators.py in inner_f(*args, **kwargs)
44 )
45 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 46 return f(**kwargs)
47 return inner_f
48
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in regplot(x, y, data, x_estimator, x_bins, x_ci, scatter, fit_reg, ci, n_boot, units, seed, order, logistic, lowess, robust, logx, x_partial, y_partial, truncate, dropna, x_jitter, y_jitter, label, color, marker, scatter_kws, line_kws, ax)
861 scatter_kws["marker"] = marker
862 line_kws = {} if line_kws is None else copy.copy(line_kws)
--> 863 plotter.plot(ax, scatter_kws, line_kws)
864 return ax
865
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in plot(self, ax, scatter_kws, line_kws)
368
369 if self.fit_reg:
--> 370 self.lineplot(ax, line_kws)
371
372 # Label the axes
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in lineplot(self, ax, kws)
411 """Draw the model."""
412 # Fit the regression model
--> 413 grid, yhat, err_bands = self.fit_regression(ax)
414 edges = grid[0], grid[-1]
415
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in fit_regression(self, ax, x_range, grid)
209 from statsmodels.genmod.families import Binomial
210 yhat, yhat_boots = self.fit_statsmodels(grid, GLM,
--> 211 family=Binomial())
212 elif self.lowess:
213 ci = None
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in fit_statsmodels(self, grid, model, **kwargs)
279 return yhat
280
--> 281 yhat = reg_func(X, y)
282 if self.ci is None:
283 return yhat, None
~/anaconda3/lib/python3.7/site-packages/seaborn/regression.py in reg_func(_x, _y)
273 def reg_func(_x, _y):
274 try:
--> 275 yhat = model(_y, _x, **kwargs).fit().predict(grid)
276 except glm.PerfectSeparationError:
277 yhat = np.empty(len(grid))
~/anaconda3/lib/python3.7/site-packages/statsmodels/genmod/generalized_linear_model.py in __init__(self, endog, exog, family, offset, exposure, freq_weights, var_weights, missing, **kwargs)
289 offset=offset, exposure=exposure,
290 freq_weights=freq_weights,
--> 291 var_weights=var_weights, **kwargs)
292 self._check_inputs(family, self.offset, self.exposure, self.endog,
293 self.freq_weights, self.var_weights)
~/anaconda3/lib/python3.7/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
214
215 def __init__(self, endog, exog=None, **kwargs):
--> 216 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
217 self.initialize()
218
~/anaconda3/lib/python3.7/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
66 hasconst = kwargs.pop('hasconst', None)
67 self.data = self._handle_data(endog, exog, missing, hasconst,
---> 68 **kwargs)
69 self.k_constant = self.data.k_constant
70 self.exog = self.data.exog
~/anaconda3/lib/python3.7/site-packages/statsmodels/base/model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
89
90 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
---> 91 data = handle_data(endog, exog, missing, hasconst, **kwargs)
92 # kwargs arrays could have changed, easier to just attach here
93 for key in kwargs:
~/anaconda3/lib/python3.7/site-packages/statsmodels/base/data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
631 exog = np.asarray(exog)
632
--> 633 klass = handle_data_class_factory(endog, exog)
634 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
635 **kwargs)
~/anaconda3/lib/python3.7/site-packages/statsmodels/base/data.py in handle_data_class_factory(endog, exog)
611 if data_util._is_using_ndarray_type(endog, exog):
612 klass = ModelData
--> 613 elif data_util._is_using_pandas(endog, exog):
614 klass = PandasData
615 elif data_util._is_using_patsy(endog, exog):
~/anaconda3/lib/python3.7/site-packages/statsmodels/tools/data.py in _is_using_pandas(endog, exog)
99
100 def _is_using_pandas(endog, exog):
--> 101 from statsmodels.compat.pandas import data_klasses as klasses
102 return (isinstance(endog, klasses) or isinstance(exog, klasses))
103
~/anaconda3/lib/python3.7/site-packages/statsmodels/compat/pandas.py in <module>
21 except ImportError:
22 from pandas.tseries import frequencies
---> 23 data_klasses = (pandas.Series, pandas.DataFrame, pandas.Panel)
24 else:
25 try:
~/anaconda3/lib/python3.7/site-packages/pandas/__init__.py in __getattr__(name)
242 return _SparseArray
243
--> 244 raise AttributeError(f"module 'pandas' has no attribute '{name}'")
245
246
AttributeError: module 'pandas' has no attribute 'Panel'

you are using the latest version of pandas library where Panal is removed from pandas version 0.25 and onward

TypeError: unhashable type: 'numpy.ndarray' when trying to plot a DataFrame

I am new to Python and trying to create a plot graph from a DataFrame.
I used the following piece of code:
predictions= list()
for the in range (10):
predicted= StartARIMAForecasting(RegistrationRates, 5,1,0)
predictions.append(predicted)
RegistrationRates.append(predicted)
data = {'Year':['2016','2017','2018','2019','2020','2021','2022','2023','2024','2025'], 'Registration Rate':predictions}
resultdf = pd.DataFrame(data)
print(resultdf)
plt.xlabel('Year')
plt.ylabel('Registration Rate')
plt.plot(resultdf)
Following output is seen:
0 2016 [50.68501406476124]
1 2017 [52.41297372600995]
2 2018 [54.0703599343735]
3 2019 [53.58327982434545]
4 2020 [55.647237533704754]
5 2021 [54.398197822219714]
6 2022 [55.06459335430334]
7 2023 [56.00171430250292]
8 2024 [55.70449088032122]
9 2025 [57.7127557392168]
but blank graph is plotted with following error:
TypeError: unhashable type: 'numpy.ndarray'
Full stack-trace is provided below:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-53-1d843e3f6a23> in <module>
58 plt.xlabel('Year')
59 plt.ylabel('Registration Rate')
---> 60 plt.plot(resultdf)
61
62 root.mainloop()
~\Anaconda3\lib\site-packages\matplotlib\pyplot.py in plot(*args, **kwargs)
3356 mplDeprecation)
3357 try:
-> 3358 ret = ax.plot(*args, **kwargs)
3359 finally:
3360 ax._hold = washold
~\Anaconda3\lib\site-packages\matplotlib\__init__.py in inner(ax, *args, **kwargs)
1853 "the Matplotlib list!)" % (label_namer, func.__name__),
1854 RuntimeWarning, stacklevel=2)
-> 1855 return func(ax, *args, **kwargs)
1856
1857 inner.__doc__ = _add_data_doc(inner.__doc__,
~\Anaconda3\lib\site-packages\matplotlib\axes\_axes.py in plot(self, *args, **kwargs)
1525 kwargs = cbook.normalize_kwargs(kwargs, _alias_map)
1526
-> 1527 for line in self._get_lines(*args, **kwargs):
1528 self.add_line(line)
1529 lines.append(line)
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in _grab_next_args(self, *args, **kwargs)
404 this += args[0],
405 args = args[1:]
--> 406 for seg in self._plot_args(this, kwargs):
407 yield seg
408
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in _plot_args(self, tup, kwargs)
381 x, y = index_of(tup[-1])
382
--> 383 x, y = self._xy_from_xy(x, y)
384
385 if self.command == 'plot':
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in _xy_from_xy(self, x, y)
214 if self.axes.xaxis is not None and self.axes.yaxis is not None:
215 bx = self.axes.xaxis.update_units(x)
--> 216 by = self.axes.yaxis.update_units(y)
217
218 if self.command != 'plot':
~\Anaconda3\lib\site-packages\matplotlib\axis.py in update_units(self, data)
1467 neednew = self.converter != converter
1468 self.converter = converter
-> 1469 default = self.converter.default_units(data, self)
1470 if default is not None and self.units is None:
1471 self.set_units(default)
~\Anaconda3\lib\site-packages\matplotlib\category.py in default_units(data, axis)
113 # default_units->axis_info->convert
114 if axis.units is None:
--> 115 axis.set_units(UnitData(data))
116 else:
117 axis.units.update(data)
~\Anaconda3\lib\site-packages\matplotlib\category.py in __init__(self, data)
180 self._counter = itertools.count(start=0)
181 if data is not None:
--> 182 self.update(data)
183
184 def update(self, data):
~\Anaconda3\lib\site-packages\matplotlib\category.py in update(self, data)
197 data = np.atleast_1d(np.array(data, dtype=object))
198
--> 199 for val in OrderedDict.fromkeys(data):
200 if not isinstance(val, VALID_TYPES):
201 raise TypeError("{val!r} is not a string".format(val=val))
TypeError: unhashable type: 'numpy.ndarray'

If you check the type of your column 'Registration Rate', you will see that it's type of numpy.ndarray as shown in the error.
type(resultdf['Registration Rate'][0])
So, maybe modify your predictions creation to make it a single element?
predictions= list()
for the in range (10):
predicted= StartARIMAForecasting(RegistrationRates, 5,1,0)
# predicted is a numpy.ndarray, len = 1
p = predicted[0]
predictions.append(p)
Then run your code a gain.

pandas Series' object has no attribute 'find'

I am trying to do simple plot of data and getting the following error.. any help is very much appreciated
AttributeError: 'Series' object has no attribute 'find'
Versions :
python3 ,
matplotlib (2.0.2) ,
pandas (0.20.3) ,
jupyter (1.0.0).
Code:
import pandas as pd
import matplotlib.pyplot as plt
pd_hr_data = pd.read_csv("/Users/pc/Downloads/HR_comma_sep.csv")
#print(pd_hr_data['average_montly_hours'],pd_hr_data['sales'])
take_ten_data = pd_hr_data[0:19]
x = take_ten_data['average_montly_hours'].astype(int)
y = take_ten_data['sales'].astype(str)
print(type(x[0]))
print(type(y[0]))
#print(x,y) ---- this gives me all the 20 values
#print(type(y[0]))
plt.plot(x,y)
plt.show()
Out Put / Error:
-
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
in ()
9 #print(type(y[0]))
10
---> 11 plt.plot(x,y)
12 plt.show()
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/pyplot.py
in plot(*args, **kwargs)
3315 mplDeprecation)
3316 try:
-> 3317 ret = ax.plot(*args, **kwargs)
3318 finally:
3319 ax._hold = washold
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/__init__.py
in inner(ax, *args, **kwargs)
1896 warnings.warn(msg % (label_namer, func.__name__),
1897 RuntimeWarning, stacklevel=2)
-> 1898 return func(ax, *args, **kwargs)
1899 pre_doc = inner.__doc__
1900 if pre_doc is None:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/axes/_axes.py
in plot(self, *args, **kwargs)
1404 kwargs = cbook.normalize_kwargs(kwargs, _alias_map)
1405
-> 1406 for line in self._get_lines(*args, **kwargs):
1407 self.add_line(line)
1408 lines.append(line)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/axes/_base.py
in _grab_next_args(self, *args, **kwargs)
405 return
406 if len(remaining) <= 3:
--> 407 for seg in self._plot_args(remaining, kwargs):
408 yield seg
409 return
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/axes/_base.py
in _plot_args(self, tup, kwargs)
355 ret = []
356 if len(tup) > 1 and is_string_like(tup[-1]):
--> 357 linestyle, marker, color = _process_plot_format(tup[-1])
358 tup = tup[:-1]
359 elif len(tup) == 3:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/axes/_base.py
in _process_plot_format(fmt)
92 # handle the multi char special cases and strip them from the
93 # string
---> 94 if fmt.find('--') >= 0:
95 linestyle = '--'
96 fmt = fmt.replace('--', '')
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pandas/core/generic.py
in __getattr__(self, name)
3079 if name in self._info_axis:
3080 return self[name]
-> 3081 return object.__getattribute__(self, name)
3082
3083 def __setattr__(self, name, value):
AttributeError: 'Series' object has no attribute 'find'

I think you can use DataFrame.plot with define x and y by columns names, because it better support plotting non numeric values:
take_ten_data = pd_hr_data[0:19]
x = take_ten_data['average_montly_hours'].astype(int)
y = take_ten_data['sales'].astype(str)
take_ten_data.plot(x='average_montly_hours', y='sales')
#working without x,y also, but less readable
#take_ten_data.plot('average_montly_hours','sales')
plt.show()
Sample:
take_ten_data = pd.DataFrame({'average_montly_hours':[3,10,12], 'sales':[10,20,30]})
x = take_ten_data['average_montly_hours'].astype(int)
y = take_ten_data['sales'].astype(str)
take_ten_data.plot(x='average_montly_hours', y='sales')
plt.show()
But if all values are numeric it works nice:
take_ten_data = pd.DataFrame({'average_montly_hours':[3,10,12], 'sales':['10','20','30']})
x = take_ten_data['average_montly_hours'].astype(int)
#convert to int if necessary
y = take_ten_data['sales'].astype(int)
plt.plot(x,y)
plt.show()

Following worked for me and hope it helps.... Issue was mixing differnt data types for plotting.
import pandas as pd
import matplotlib.pyplot as plt
pd_hr_data = pd.read_csv("/Users/pc/Downloads/HR_comma_sep.csv")
take_ten_data = pd_hr_data[0:4]
y = take_ten_data['average_montly_hours'].astype(int)
x = [1,2,3,4] ----this is can be autogenerated based on the series/matrix size
names = take_ten_data['sales']
plt.bar(x,y, align='center')
#plt.plot(x,y) ---- use this if you want
plt.xticks(x, names)
plt.show()