Develop Reference

OLS Statsmodels formula: Returns an ValueError: zero-size array to reduction operation maximum which has no identity

Hey I am doing multiple OLS regressions for some cross-sectional data iterating through the months. I encounter for the forth month a ValueError: zero-size array to reduction operation maximum which has no identity. But I do not know why. The data has no NaNs, I have tested this with dropna since it was suggested in another Question Link:
df_month.dropna(how='all')
And the zero in each months data is due to the normalization of the data, which does not cause any trouble during the first three iterations only in the fourth. What's also weird is that if I stop the loop before the OLS regression is executed in the fourth line and then run the regression again by hand in another cell it just works fine. Could this issue be due to the storing?
Here is my code an data to replicate the error:
import statsmodels.formula.api as smf #ols (minor letters)
import pandas as pd
import numpy as np
df = pd.read_csv('df_all.csv', index_col='Instrument', sep=',', decimal='.')
df.drop(columns='Unnamed: 0', inplace=True)
#Creates an array with all the years to iterate through single year
years = df_all['Date'].dt.year.unique()
df_store = pd.DataFrame(index=[], columns=['year', 'month', 'R2_adj'])
for year in years:
df_year = df_all[df_all['Date'].dt.year == year]
df_year_t1 = df_all[df_all['Date'].dt.year == year+1]
Jan_date = df_year['Date'][0]
year_start = df_year[(df_year['Date'] == Jan_date) & (df_year['HQ'] == 'United States of America')
& (df_year['ESG'] > 0)]
year_start_firms = year_start.index.unique()
df_year_firms = df_year[['Date', 'eTR', 'MC', 'ESG']].loc[year_start_firms]
df_year_t1 = df_year_t1[['Date', 'eTR', 'MC', 'ESG']]
print(year)
print(" ")
#Normalizes the ESG Scores to the interval (0; 1) and substitues it in; 0.5 is the mean
df = df_year_firms[['ESG']]
Normalized_ESG_year = (df - df.min()) / (df.max() - df.min())
df_year_firms_norm = df_year_firms
df_year_firms_norm[['ESG_norm']] = Normalized_ESG_year.values
df_year_firms_norm = df_year_firms_norm.drop('ESG', axis=1)
df_year_firms_norm = df_year_firms_norm.ffill(axis=0)
df_year_firms_norm.loc[:, 'Month'] = df_year_firms_norm['Date'].dt.month.values.reshape(len(df_year_firms_norm), 1)
df_year_t1.loc[:, 'Month'] = df_year_t1['Date'].dt.month.values.reshape(len(df_year_t1), 1)
data = pd.merge(df_year_firms_norm, df_year_t1.iloc[:, [0,1,-1]], how='inner', on=['Instrument', 'Month'], suffixes=('_t', '_t1'))
#Resets index
data.reset_index(inplace=True)
#Monthwise iteration within the year loop
for month in range(1, 13, 1):
df_month = data[data['Month'] == month]
#ols by statsmodels.formula.api = smf (ols with minor letters)
#DataFrame input
#smf not sm (statsmodels.formula.api instead of statsmodels.api)
ESG_ols = smf.ols(formula = 'eTR_t1 ~ ESG_norm', data=df_month).fit(cov_type='HAC',cov_kwds={'maxlags':0})
ESG_ols_tstat = ESG_ols.tvalues
ESG_ols_coeff = ESG_ols.params
results_df = pd.DataFrame({
'ESG_ols_coeff':ESG_ols_coeff, 'ESG_ols_tstat':ESG_ols_tstat},
index = ['Intercept', 'ESG'])
#Produces the table
df_output = summary_col(
results=[ESG_ols], stars=True, float_format='%0.4f',
model_names=['ESG_ols'],
info_dict={'N':lambda x: "{0:d}".format(int(x.nobs))},
regressor_order = ['Intercept', 'ESG_norm'])
helper = pd.DataFrame(data=[[year, month, ESG_ols.rsquared_adj]],
columns=['year', 'month', 'R2_adj'])
df_store = df_store.append(helper)
print(month)
break
df_store
I am also happy for any suggestions in efficiency!
As requested, here is the full Traceback:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_8408/1348884998.py in <module>
91 # break
92 #smf not sm (statsmodels.formula.api instead of statsmodels.api)
---> 93 ESG_ols = smf.ols(formula = 'eTR_t1 ~ ESG_norm', data=df_month).fit(cov_type='HAC',cov_kwds={'maxlags':1})
94 #!Assumption: maxlags=0 should be reasonable since we do not have any TS analysis, right?
95 ESG_ols_tstat = ESG_ols.tvalues
~\anaconda3\lib\site-packages\statsmodels\base\model.py in from_formula(cls, formula, data, subset, drop_cols, *args, **kwargs)
193 'formula': formula, # attach formula for unpckling
194 'design_info': design_info})
--> 195 mod = cls(endog, exog, *args, **kwargs)
196 mod.formula = formula
197
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
870 def __init__(self, endog, exog=None, missing='none', hasconst=None,
871 **kwargs):
--> 872 super(OLS, self).__init__(endog, exog, missing=missing,
873 hasconst=hasconst, **kwargs)
874 if "weights" in self._init_keys:
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
701 else:
702 weights = weights.squeeze()
--> 703 super(WLS, self).__init__(endog, exog, missing=missing,
704 weights=weights, hasconst=hasconst, **kwargs)
705 nobs = self.exog.shape[0]
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, **kwargs)
188 """
189 def __init__(self, endog, exog, **kwargs):
--> 190 super(RegressionModel, self).__init__(endog, exog, **kwargs)
191 self._data_attr.extend(['pinv_wexog', 'weights'])
192
~\anaconda3\lib\site-packages\statsmodels\base\model.py in __init__(self, endog, exog, **kwargs)
235
236 def __init__(self, endog, exog=None, **kwargs):
--> 237 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
238 self.initialize()
239
~\anaconda3\lib\site-packages\statsmodels\base\model.py in __init__(self, endog, exog, **kwargs)
75 missing = kwargs.pop('missing', 'none')
76 hasconst = kwargs.pop('hasconst', None)
---> 77 self.data = self._handle_data(endog, exog, missing, hasconst,
78 **kwargs)
79 self.k_constant = self.data.k_constant
~\anaconda3\lib\site-packages\statsmodels\base\model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
99
100 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 101 data = handle_data(endog, exog, missing, hasconst, **kwargs)
102 # kwargs arrays could have changed, easier to just attach here
103 for key in kwargs:
~\anaconda3\lib\site-packages\statsmodels\base\data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
670
671 klass = handle_data_class_factory(endog, exog)
--> 672 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
673 **kwargs)
~\anaconda3\lib\site-packages\statsmodels\base\data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
85 self.const_idx = None
86 self.k_constant = 0
---> 87 self._handle_constant(hasconst)
88 self._check_integrity()
89 self._cache = {}
~\anaconda3\lib\site-packages\statsmodels\base\data.py in _handle_constant(self, hasconst)
129 # detect where the constant is
130 check_implicit = False
--> 131 exog_max = np.max(self.exog, axis=0)
132 if not np.isfinite(exog_max).all():
133 raise MissingDataError('exog contains inf or nans')
<__array_function__ internals> in amax(*args, **kwargs)
~\anaconda3\lib\site-packages\numpy\core\fromnumeric.py in amax(a, axis, out, keepdims, initial, where)
2731 5
2732 """
-> 2733 return _wrapreduction(a, np.maximum, 'max', axis, None, out,
2734 keepdims=keepdims, initial=initial, where=where)
2735
~\anaconda3\lib\site-packages\numpy\core\fromnumeric.py in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs)
85 return reduction(axis=axis, out=out, **passkwargs)
86
---> 87 return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
88
89
ValueError: zero-size array to reduction operation maximum which has no identity

I was reluctant to use this approach but it works and I still get results even for those month where there is supposed to be a lack of data.
I found the idea here Overcom ValueError for empty array
try: #Catches the upcoming Value Error
results = smf.ols(formula = 'eTR_t1 ~ ESG_norm', data=df_month).fit(cov_type='HAC',cov_kwds={'maxlags':0})
except ValueError:
pass
Thank you #Josef for the suggestions and the help.

Regression ValueError: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data)

I have a data frame 'df' that has missing column values. I want to fill in the missing/NaN values in the Avg Monthly Long Distance Charges column through prediction (regression) using the other column values. Then, replace the NaN values with the new values found.
I received the following error message when executing my code. Is there something that I am doing wrong?
Data frame: 'df'
Customer ID,Gender,Age,Married,Number of Dependents,City,Zip Code,Latitude,Longitude,Number of Referrals,Tenure in Months,Offer,Phone Service,Avg Monthly Long Distance Charges,Multiple Lines,Internet Service,Internet Type,Avg Monthly GB Download,Online Security,Online Backup,Device Protection Plan,Premium Tech Support,Streaming TV,Streaming Movies,Streaming Music,Unlimited Data,Contract,Paperless Billing,Payment Method,Monthly Charge,Total Charges,Total Refunds,Total Extra Data Charges,Total Long Distance Charges,Total Revenue,Customer Status,Churn Category,Churn Reason
0002-ORFBO,Female,37,Yes,0,Frazier Park,93225,34.827662,-118.999073,2,9,None,Yes,42.39,No,Yes,Cable,16,No,Yes,No,Yes,Yes,No,No,Yes,One Year,Yes,Credit Card,65.6,593.3,0,0,381.51,974.81,Stayed,,
0003-MKNFE,Male,46,No,0,Glendale,91206,34.162515,-118.203869,0,9,None,Yes,10.69,Yes,Yes,Cable,10,No,No,No,No,No,Yes,Yes,No,Month-to-Month,No,Credit Card,-4,542.4,38.33,10,96.21,610.28,Stayed,,
0004-TLHLJ,Male,50,No,0,Costa Mesa,92627,33.645672,-117.922613,0,4,Offer E,Yes,33.65,No,Yes,Fiber Optic,30,No,No,Yes,No,No,No,No,Yes,Month-to-Month,Yes,Bank Withdrawal,73.9,280.85,0,0,134.6,415.45,Churned,Competitor,Competitor had better devices
0011-IGKFF,Male,78,Yes,0,Martinez,94553,38.014457,-122.115432,1,13,Offer D,Yes,27.82,No,Yes,Fiber Optic,4,No,Yes,Yes,No,Yes,Yes,No,Yes,Month-to-Month,Yes,Bank Withdrawal,98,1237.85,0,0,361.66,1599.51,Churned,Dissatisfaction,Product dissatisfaction
0013-EXCHZ,Female,75,Yes,0,Camarillo,93010,34.227846,-119.079903,3,3,None,Yes,7.38,No,Yes,Fiber Optic,11,No,No,No,Yes,Yes,No,No,Yes,Month-to-Month,Yes,Credit Card,83.9,267.4,0,0,22.14,289.54,Churned,Dissatisfaction,Network reliability
0013-MHZWF,Female,23,No,3,Midpines,95345,37.581496,-119.972762,0,9,Offer E,Yes,16.77,No,Yes,Cable,73,No,No,No,Yes,Yes,Yes,Yes,Yes,Month-to-Month,Yes,Credit Card,69.4,571.45,0,0,150.93,722.38,Stayed,,
0013-SMEOE,Female,67,Yes,0,Lompoc,93437,34.757477,-120.550507,1,71,Offer A,Yes,9.96,No,Yes,Fiber Optic,14,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Two Year,Yes,Bank Withdrawal,109.7,7904.25,0,0,707.16,8611.41,Stayed,,
0014-BMAQU,Male,52,Yes,0,Napa,94558,38.489789,-122.27011,8,63,Offer B,Yes,12.96,Yes,Yes,Fiber Optic,7,Yes,No,No,Yes,No,No,No,No,Two Year,Yes,Credit Card,84.65,5377.8,0,20,816.48,6214.28,Stayed,,
0015-UOCOJ,Female,68,No,0,Simi Valley,93063,34.296813,-118.685703,0,7,Offer E,Yes,10.53,No,Yes,DSL,21,Yes,No,No,No,No,No,No,Yes,Two Year,Yes,Bank Withdrawal,48.2,340.35,0,0,73.71,414.06,Stayed,,
0016-QLJIS,Female,43,Yes,1,Sheridan,95681,38.984756,-121.345074,3,65,None,Yes,28.46,Yes,Yes,Cable,14,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Two Year,Yes,Credit Card,90.45,5957.9,0,0,1849.9,7807.8,Stayed,,
0017-DINOC,Male,47,No,0,Rancho Santa Fe,92091,32.99356,-117.207121,0,54,None,No,,,Yes,Cable,10,Yes,No,No,Yes,Yes,No,No,Yes,Two Year,No,Credit Card,45.2,2460.55,0,0,0,2460.55,Stayed,,
0017-IUDMW,Female,25,Yes,2,Sunnyvale,94086,37.378541,-122.020456,2,72,None,Yes,16.01,Yes,Yes,Fiber Optic,59,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Yes,Two Year,Yes,Credit Card,116.8,8456.75,0,0,1152.72,9609.47,Stayed,,
0018-NYROU,Female,58,Yes,0,Antelope,95843,38.715498,-121.363411,0,5,None,Yes,18.65,No,Yes,Fiber Optic,10,No,No,No,No,No,No,No,Yes,Month-to-Month,Yes,Bank Withdrawal,68.95,351.5,0,0,93.25,444.75,Stayed,,
0019-EFAEP,Female,32,No,0,La Mesa,91942,32.782501,-117.01611,0,72,Offer A,Yes,2.25,Yes,Yes,Fiber Optic,16,Yes,Yes,Yes,No,Yes,No,No,Yes,Two Year,Yes,Bank Withdrawal,101.3,7261.25,0,0,162,7423.25,Stayed,,
0019-GFNTW,Female,39,No,0,Los Olivos,93441,34.70434,-120.02609,0,56,None,No,,,Yes,DSL,19,Yes,Yes,Yes,Yes,No,No,No,Yes,Two Year,No,Bank Withdrawal,45.05,2560.1,0,0,0,2560.1,Stayed,,
0020-INWCK,Female,58,Yes,2,Woodlake,93286,36.464635,-119.094348,9,71,Offer A,Yes,27.26,Yes,Yes,Fiber Optic,12,No,Yes,Yes,No,No,Yes,Yes,Yes,Two Year,Yes,Credit Card,95.75,6849.4,0,0,1935.46,8784.86,Stayed,,
0020-JDNXP,Female,52,Yes,1,Point Reyes Station,94956,38.060264,-122.830646,0,34,None,No,,,Yes,DSL,20,Yes,No,Yes,Yes,Yes,Yes,Yes,Yes,One Year,No,Credit Card,61.25,1993.2,0,0,0,1993.2,Stayed,,
0021-IKXGC,Female,72,No,0,San Marcos,92078,33.119028,-117.166036,0,1,Offer E,Yes,7.77,Yes,Yes,Fiber Optic,22,No,No,No,No,No,No,No,Yes,One Year,Yes,Bank Withdrawal,72.1,72.1,0,0,7.77,79.87,Joined,,
0022-TCJCI,Male,79,No,0,Daly City,94015,37.680844,-122.48131,0,45,None,Yes,10.67,No,Yes,DSL,17,Yes,No,Yes,No,No,Yes,No,Yes,One Year,No,Credit Card,62.7,2791.5,0,0,480.15,3271.65,Churned,Dissatisfaction,Limited range of services
My code:
# Let X = predictor variable and y = target variable
X2 = pd.DataFrame(df[['Monthly Charge', 'Total Revenue']])
y2 = pd.DataFrame(df[['Multiple Lines']])
# Add a constant variable to the predictor variables
X = sm.add_constant(X2)
model02 = sm.OLS(y2, X2).fit()
df['Multiple Lines'].fillna(sm.OLS(y2, X2).fit(), inplace=True)
Error Message: ValueError: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data).
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/var/folders/wv/42dn23fd1cb0czpvqdnb6zw00000gn/T/ipykernel_15181/1879921247.py in <module>
5 # Add a constant variable to the predictor variables
6 X = sm.add_constant(X2)
----> 7 model02 = sm.OLS(y2, X2).fit()
8 df['Multiple Lines'].fillna(sm.OLS(y2, X2).fit(), inplace=True)
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
888 "An exception will be raised in the next version.")
889 warnings.warn(msg, ValueWarning)
--> 890 super(OLS, self).__init__(endog, exog, missing=missing,
891 hasconst=hasconst, **kwargs)
892 if "weights" in self._init_keys:
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
715 else:
716 weights = weights.squeeze()
--> 717 super(WLS, self).__init__(endog, exog, missing=missing,
718 weights=weights, hasconst=hasconst, **kwargs)
719 nobs = self.exog.shape[0]
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, **kwargs)
189 """
190 def __init__(self, endog, exog, **kwargs):
--> 191 super(RegressionModel, self).__init__(endog, exog, **kwargs)
192 self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog', 'weights'])
193
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
265
266 def __init__(self, endog, exog=None, **kwargs):
--> 267 super().__init__(endog, exog, **kwargs)
268 self.initialize()
269
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
90 missing = kwargs.pop('missing', 'none')
91 hasconst = kwargs.pop('hasconst', None)
---> 92 self.data = self._handle_data(endog, exog, missing, hasconst,
93 **kwargs)
94 self.k_constant = self.data.k_constant
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
130
131 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 132 data = handle_data(endog, exog, missing, hasconst, **kwargs)
133 # kwargs arrays could have changed, easier to just attach here
134 for key in kwargs:
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
671
672 klass = handle_data_class_factory(endog, exog)
--> 673 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
674 **kwargs)
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
80 self.orig_endog = endog
81 self.orig_exog = exog
---> 82 self.endog, self.exog = self._convert_endog_exog(endog, exog)
83
84 self.const_idx = None
~/opt/miniconda3/lib/python3.9/site-packages/statsmodels/base/data.py in _convert_endog_exog(self, endog, exog)
505 exog = exog if exog is None else np.asarray(exog)
506 if endog.dtype == object or exog is not None and exog.dtype == object:
--> 507 raise ValueError("Pandas data cast to numpy dtype of object. "
508 "Check input data with np.asarray(data).")
509 return super(PandasData, self)._convert_endog_exog(endog, exog)
ValueError: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data).

your y variable (y2) is of type object. Before feeding into the model, convert the y variable to int/float.
For example
model02 = sm.OLS(pd.get_dummies(y2), X2).fit()
pd.get_dummies is one option. find the one which is more appropriate to your use case . For ex: Label encoding

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

Why am I not able to use the same data set in a matplotlib.pyplot histogram after using it in a graph?

I was going through some of the Quantitative Finance tutorials on Quantopia, when I encountered a problem in creating a histogram. Originally, I used my data set, X, and plotted it in a graph. The graph was displayed in the notebook, but when I tried to run the last line in the code shown, I got a number of traceback errors.
I managed to make the histogram by removing the lines of code which plotted X to a graph, but I'm confused as to why I can't create both a graph and a histogram. Is the object being changed somewhere along the way? My apologies if this is something rudimentary, I am fairly new to coding, and this is my first question on Stack Exchange. If it helps, the Quantopia notebooks are on Python 2.7. Thanks, and have a great day.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data = get_pricing('MSFT', start_date='2012-1-1', end_date='2015-6-1')
X = data['price']
plt.plot(X.index, X.values)
plt.ylabel('Price')
plt.legend(['MSFT']);
R = X.pct_change()[1:]
plt.hist(R, bins = 20)
Here's the error:
ValueErrorTraceback (most recent call last)
/usr/local/lib/python2.7/dist-packages/IPython/core/formatters.pyc in __call__(self, obj)
332 pass
333 else:
--> 334 return printer(obj)
335 # Finally look for special method names
336 method = get_real_method(obj, self.print_method)
/usr/local/lib/python2.7/dist-packages/IPython/core/pylabtools.pyc in <lambda>(fig)
245
246 if 'png' in formats:
--> 247 png_formatter.for_type(Figure, lambda fig: print_figure(fig, 'png', **kwargs))
248 if 'retina' in formats or 'png2x' in formats:
249 png_formatter.for_type(Figure, lambda fig: retina_figure(fig, **kwargs))
/usr/local/lib/python2.7/dist-packages/IPython/core/pylabtools.pyc in print_figure(fig, fmt, bbox_inches, **kwargs)
129
130 bytes_io = BytesIO()
--> 131 fig.canvas.print_figure(bytes_io, **kw)
132 data = bytes_io.getvalue()
133 if fmt == 'svg':
/usr/local/lib/python2.7/dist-packages/matplotlib/backend_bases.pyc in print_figure(self, filename, dpi, facecolor, edgecolor, orientation, format, **kwargs)
2178 orientation=orientation,
2179 dryrun=True,
-> 2180 **kwargs)
2181 renderer = self.figure._cachedRenderer
2182 bbox_inches = self.figure.get_tightbbox(renderer)
/usr/local/lib/python2.7/dist-packages/matplotlib/backends/backend_agg.pyc in print_png(self, filename_or_obj, *args, **kwargs)
525
526 def print_png(self, filename_or_obj, *args, **kwargs):
--> 527 FigureCanvasAgg.draw(self)
528 renderer = self.get_renderer()
529 original_dpi = renderer.dpi
/usr/local/lib/python2.7/dist-packages/matplotlib/backends/backend_agg.pyc in draw(self)
472
473 try:
--> 474 self.figure.draw(self.renderer)
475 finally:
476 RendererAgg.lock.release()
/usr/local/lib/python2.7/dist-packages/matplotlib/artist.pyc in draw_wrapper(artist, renderer, *args, **kwargs)
59 def draw_wrapper(artist, renderer, *args, **kwargs):
60 before(artist, renderer)
---> 61 draw(artist, renderer, *args, **kwargs)
62 after(artist, renderer)
63
/usr/local/lib/python2.7/dist-packages/matplotlib/figure.pyc in draw(self, renderer)
1157 dsu.sort(key=itemgetter(0))
1158 for zorder, a, func, args in dsu:
-> 1159 func(*args)
1160
1161 renderer.close_group('figure')
/usr/local/lib/python2.7/dist-packages/matplotlib/artist.pyc in draw_wrapper(artist, renderer, *args, **kwargs)
59 def draw_wrapper(artist, renderer, *args, **kwargs):
60 before(artist, renderer)
---> 61 draw(artist, renderer, *args, **kwargs)
62 after(artist, renderer)
63
/usr/local/lib/python2.7/dist-packages/matplotlib/axes/_base.pyc in draw(self, renderer, inframe)
2322
2323 for zorder, a in dsu:
-> 2324 a.draw(renderer)
2325
2326 renderer.close_group('axes')
/usr/local/lib/python2.7/dist-packages/matplotlib/artist.pyc in draw_wrapper(artist, renderer, *args, **kwargs)
59 def draw_wrapper(artist, renderer, *args, **kwargs):
60 before(artist, renderer)
---> 61 draw(artist, renderer, *args, **kwargs)
62 after(artist, renderer)
63
/usr/local/lib/python2.7/dist-packages/matplotlib/axis.pyc in draw(self, renderer, *args, **kwargs)
1104 renderer.open_group(__name__)
1105
-> 1106 ticks_to_draw = self._update_ticks(renderer)
1107 ticklabelBoxes, ticklabelBoxes2 = self._get_tick_bboxes(ticks_to_draw,
1108 renderer)
/usr/local/lib/python2.7/dist-packages/matplotlib/axis.pyc in _update_ticks(self, renderer)
947
948 interval = self.get_view_interval()
--> 949 tick_tups = [t for t in self.iter_ticks()]
950 if self._smart_bounds:
951 # handle inverted limits
/usr/local/lib/python2.7/dist-packages/matplotlib/axis.pyc in iter_ticks(self)
890 Iterate through all of the major and minor ticks.
891 """
--> 892 majorLocs = self.major.locator()
893 majorTicks = self.get_major_ticks(len(majorLocs))
894 self.major.formatter.set_locs(majorLocs)
/usr/local/lib/python2.7/dist-packages/matplotlib/dates.pyc in __call__(self)
1004 def __call__(self):
1005 'Return the locations of the ticks'
-> 1006 self.refresh()
1007 return self._locator()
1008
/usr/local/lib/python2.7/dist-packages/matplotlib/dates.pyc in refresh(self)
1024 def refresh(self):
1025 'Refresh internal information based on current limits.'
-> 1026 dmin, dmax = self.viewlim_to_dt()
1027 self._locator = self.get_locator(dmin, dmax)
1028
/usr/local/lib/python2.7/dist-packages/matplotlib/dates.pyc in viewlim_to_dt(self)
768 vmin, vmax = vmax, vmin
769
--> 770 return num2date(vmin, self.tz), num2date(vmax, self.tz)
771
772 def _get_unit(self):
/usr/local/lib/python2.7/dist-packages/matplotlib/dates.pyc in num2date(x, tz)
417 tz = _get_rc_timezone()
418 if not cbook.iterable(x):
--> 419 return _from_ordinalf(x, tz)
420 else:
421 x = np.asarray(x)
/usr/local/lib/python2.7/dist-packages/matplotlib/dates.pyc in _from_ordinalf(x, tz)
269
270 ix = int(x)
--> 271 dt = datetime.datetime.fromordinal(ix).replace(tzinfo=UTC)
272
273 remainder = float(x) - ix
ValueError: ordinal must be >= 1
<matplotlib.figure.Figure at 0x7fdbbf910dd0>

statsmodels ValueError

I am having problem for my project, i have extracted data from twitter, saved it as csv and also performed data sentiment analysis but when i am trying to plot them i am unable to.
#statmodels OLS first
y, X = dmatrices('retweet_count_l ~ surge_pricing + free_rides + promo+ driver + food + controversy + regulations', data=training, return_type='dataframe')
# Define the model from above Patsy-created variables, using Statsmodels
print sm.OLS(y,X).fit().summary()
print sm.OLS(y,X).fit().params
print 'r sqd is : ', sm.OLS(y,X).fit().rsquared
rainbow = sm.stats.linear_rainbow(sm.OLS(y,X).fit())
print 'Rainbow Test for Linearity is ', rainbow
y_hat, X_hat = dmatrices('retweet_count_l ~ surge_pricing + free_rides + promo + driver + food + controversy + regulations', data=testing, return_type='dataframe')
y_pred = sm.OLS(y,X).fit().predict(X_hat)
testing['retweet_pred_smols'] = pd.Series(y_pred)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-7-b5c392dca77b> in <module>()
2 y, X = dmatrices('retweet_count_l ~ surge_pricing + free_rides + promo + driver + food + controversy + regulations', data=training, return_type='dataframe')
3 # Define the model from above Patsy-created variables, using Statsmodels
----> 4 model = sm.OLS(y,X)
5 results = model.fit()
6 print(results.summary())
/usr/lib/python2.7/dist-packages/statsmodels/regression/linear_model.pyc in __init__(self, endog, exog, missing, hasconst)
481 def __init__(self, endog, exog=None, missing='none', hasconst=None):
482 super(OLS, self).__init__(endog, exog, missing=missing,
--> 483 hasconst=hasconst)
484
485 def loglike(self, params):
/usr/lib/python2.7/dist-packages/statsmodels/regression/linear_model.pyc in __init__(self, endog, exog, weights, missing, hasconst)
383 weights = weights.squeeze()
384 super(WLS, self).__init__(endog, exog, missing=missing,
--> 385 weights=weights, hasconst=hasconst)
386 nobs = self.exog.shape[0]
387 weights = self.weights
/usr/lib/python2.7/dist-packages/statsmodels/regression/linear_model.pyc in __init__(self, endog, exog, **kwargs)
77 """
78 def __init__(self, endog, exog, **kwargs):
---> 79 super(RegressionModel, self).__init__(endog, exog, **kwargs)
80 self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog', 'weights'])
81
/usr/lib/python2.7/dist-packages/statsmodels/base/model.pyc in __init__(self, endog, exog, **kwargs)
135 def __init__(self, endog, exog=None, **kwargs):
136 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
--> 137 self.initialize()
138
139 def initialize(self):
/usr/lib/python2.7/dist-packages/statsmodels/regression/linear_model.pyc in initialize(self)
86 # overwrite nobs from class Model:
87 self.nobs = float(self.wexog.shape[0])
---> 88 self.rank = rank(self.exog)
89 self.df_model = float(self.rank - self.k_constant)
90 self.df_resid = self.nobs - self.rank
/usr/lib/python2.7/dist-packages/statsmodels/tools/tools.pyc in rank(X, cond)
380 if len(X.shape) == 2:
381 D = svdvals(X)
--> 382 return int(np.add.reduce(np.greater(D / D.max(), cond).astype(np.int32)))
383 else:
384 return int(not np.alltrue(np.equal(X, 0.)))
/usr/local/lib/python2.7/dist-packages/numpy/core/_methods.pyc in _amax(a, axis, out, keepdims)
24 # small reductions
25 def _amax(a, axis=None, out=None, keepdims=False):
---> 26 return umr_maximum(a, axis, None, out, keepdims)
27
28 def _amin(a, axis=None, out=None, keepdims=False):
ValueError: zero-size array to reduction operation maximum which has no identity

I can reproduce the error with:
In [224]: np.array([]).max()
...
ValueError: zero-size array to reduction operation maximum which has no identity
In [225]:
So tracing D.max() back ...
sm.OLS(y,X)
X must be be zero-size.
So you need to examine X. What is it's .shape? Try printing it.

I had the same issue. It was because I had some 'nan' values in my columns. After filling them with '0's the problem was solved.