Python table.SimpleTable类代码示例

    def test_simple_table_3(self):
        # Test SimpleTable.extend() as in extend down
        desired = '''
==============================
           header s1 header d1
------------------------------
stub R1 C1  10.30312  10.73999
stub R2 C1  90.30312  90.73999
           header s2 header d2
------------------------------
stub R1 C2  50.95038  50.65765
stub R2 C2  40.95038  40.65765
------------------------------
'''
        data1 = [[10.30312, 10.73999], [90.30312, 90.73999]]
        data2 = [[50.95038, 50.65765], [40.95038, 40.65765]]
        stubs1 = ['stub R1 C1', 'stub R2 C1']
        stubs2 = ['stub R1 C2', 'stub R2 C2']
        header1 = ['header s1', 'header d1']
        header2 = ['header s2', 'header d2']
        actual1 = SimpleTable(data1, header1, stubs1, txt_fmt=default_txt_fmt)
        actual2 = SimpleTable(data2, header2, stubs2, txt_fmt=default_txt_fmt)
        actual1.extend(actual2)
        actual = '\n%s\n' % actual1.as_text()
        assert_equal(desired, str(actual))

    def test_customlabel(self):
        # Limited test of custom custom labeling
        tbl = SimpleTable(table1data, test1header, test1stubs, txt_fmt=txt_fmt1)
        tbl[1][1].data = np.nan
        tbl.label_cells(custom_labeller)
        #print([[c.datatype for c in row] for row in tbl])
        desired = """
*****************************
*       * header1 * header2 *
*****************************
* stub1 *    --   *       1 *
* stub2 *    2.00 *       3 *
*****************************
"""
        actual = '\n%s\n' % tbl.as_text(missing='--')
        assert_equal(actual, desired)

    def test_simple_table_1(self):
        # Basic test, test_simple_table_1
        desired = '''
=====================
      header1 header2
---------------------
stub1 1.30312 2.73999
stub2 1.95038 2.65765
---------------------
'''
        test1data = [[1.30312, 2.73999],[1.95038, 2.65765]]
        test1stubs = ('stub1', 'stub2')
        test1header = ('header1', 'header2')
        actual = SimpleTable(test1data, test1header, test1stubs,
                             txt_fmt=default_txt_fmt)
        actual = '\n%s\n' % actual.as_text()
        assert_equal(desired, str(actual))

    def summary_find_nfact(self):
        '''provides a summary for the selection of the number of factors

        Returns
        -------
        sumstr : string
            summary of the results for selecting the number of factors

        '''
        if not hasattr(self, 'results_find_nfact'):
            self.fit_find_nfact()


        results = self.results_find_nfact
        sumstr = ''
        sumstr += '\n' + 'Best result for k, by AIC, BIC, R2_adj, L1O'
#        best = np.r_[(np.argmin(results[:,1:3],0), np.argmax(results[:,3],0),
#                     np.argmin(results[:,-1],0))]

        sumstr += '\n' + ' '*19 + '%5d %4d %6d %5d' % tuple(self.best_nfact)

        from statsmodels.iolib.table import (SimpleTable, default_txt_fmt,
                                default_latex_fmt, default_html_fmt)

        headers = 'k, AIC, BIC, R2_adj, L1O'.split(', ')
        numformat = ['%6d'] + ['%10.3f']*4 #'%10.4f'
        txt_fmt1 = dict(data_fmts = numformat)
        tabl = SimpleTable(results, headers, None, txt_fmt=txt_fmt1)

        sumstr += '\n' + "PCA regression on simulated data,"
        sumstr += '\n' + "DGP: 2 factors and 4 explanatory variables"
        sumstr += '\n' + tabl.__str__()
        sumstr += '\n' + "Notes: k is number of components of PCA,"
        sumstr += '\n' + "       constant is added additionally"
        sumstr += '\n' + "       k=0 means regression on constant only"
        sumstr += '\n' + "       L1O: sum of squared prediction errors for leave-one-out"
        return sumstr

#.........这里部分代码省略.........
          ('Model:', lambda: [results.model.__class__.__name__]),
          #('Model type:', lambda: [results.model.__class__.__name__]),
          ('Date:', lambda: [date]),
          ('Time:', lambda: time_of_day),
          ('Number of Obs:', lambda: [results.nobs]),
          #('No. of Observations:', lambda: ["%#6d" % results.nobs]),
          ('No. Observations:', lambda: ["%#6d" % results.nobs]),
          #('Df model:', lambda: [results.df_model]),
          ('Df Model:', lambda: ["%#6d" % results.df_model]),
          #TODO: check when we have non-integer df
          ('Df Residuals:', lambda: ["%#6d" % results.df_resid]),
          #('Df resid:', lambda: [results.df_resid]),
          #('df resid:', lambda: [results.df_resid]), #check capitalization
          ('Log-Likelihood:', lambda: ["%#8.5g" % results.llf]) #doesn't exist for RLM - exception
          #('Method:', lambda: [???]), #no default for this
          ])

    if title is None:
        title = results.model.__class__.__name__ + 'Regression Results'

    if gen_left is None:
        #default: General part of the summary table, Applicable to all? models
        gen_left = [('Dep. Variable:', None),
                    ('Model type:', None),
                    ('Date:', None),
                    ('No. Observations:', None)
                    ('Df model:', None),
                    ('Df resid:', None)]

        try:
            llf = results.llf
            gen_left.append(('Log-Likelihood', None))
        except: #AttributeError, NotImplementedError
            pass

        gen_right = []


    gen_title = title
    gen_header = None

    #needed_values = [k for k,v in gleft + gright if v is None] #not used anymore
    #replace missing (None) values with default values
    gen_left_ = []
    for item, value in gen_left:
        if value is None:
            value = default_items[item]()  #let KeyErrors raise exception
        gen_left_.append((item, value))
    gen_left = gen_left_

    if gen_right:
        gen_right_ = []
        for item, value in gen_right:
            if value is None:
                value = default_items[item]()  #let KeyErrors raise exception
            gen_right_.append((item, value))
        gen_right = gen_right_

    #check
    missing_values = [k for k,v in gen_left + gen_right if v is None]
    assert missing_values == [], missing_values

    #pad both tables to equal number of rows
    if gen_right:
        if len(gen_right) < len(gen_left):
            #fill up with blank lines to same length
            gen_right += [(' ', ' ')] * (len(gen_left) - len(gen_right))
        elif len(gen_right) > len(gen_left):
            #fill up with blank lines to same length, just to keep it symmetric
            gen_left += [(' ', ' ')] * (len(gen_right) - len(gen_left))

        #padding in SimpleTable doesn't work like I want
        #force extra spacing and exact string length in right table
        gen_right = [('%-21s' % ('  '+k), v) for k,v in gen_right]
        gen_stubs_right, gen_data_right = zip_longest(*gen_right) #transpose row col
        gen_table_right = SimpleTable(gen_data_right,
                                      gen_header,
                                      gen_stubs_right,
                                      title = gen_title,
                                      txt_fmt = fmt_2cols #gen_fmt
                                      )
    else:
        gen_table_right = []  #because .extend_right seems works with []


    #moved below so that we can pad if needed to match length of gen_right
    #transpose rows and columns, `unzip`
    gen_stubs_left, gen_data_left = zip_longest(*gen_left) #transpose row col

    gen_table_left = SimpleTable(gen_data_left,
                                 gen_header,
                                 gen_stubs_left,
                                 title = gen_title,
                                 txt_fmt = fmt_2cols
                                 )

    gen_table_left.extend_right(gen_table_right)
    general_table = gen_table_left

    return general_table #, gen_table_left, gen_table_right

def summary(self, yname=None, xname=None, title=0, alpha=.05,
            returns='text', model_info=None):
    """
    Parameters
    -----------
    yname : string
            optional, Default is `Y`
    xname : list of strings
            optional, Default is `X.#` for # in p the number of regressors
    Confidance interval : (0,1) not implimented
    title : string
            optional, Defualt is 'Generalized linear model'
    returns : string
              'text', 'table', 'csv', 'latex', 'html'

    Returns
    -------
    Defualt :
    returns='print'
            Prints the summarirized results

    Option :
    returns='text'
            Prints the summarirized results

    Option :
    returns='table'
             SimpleTable instance : summarizing the fit of a linear model.

    Option :
    returns='csv'
            returns a string of csv of the results, to import into a spreadsheet

    Option :
    returns='latex'
    Not implimented yet

    Option :
    returns='HTML'
    Not implimented yet


    Examples (needs updating)
    --------
    >>> import statsmodels as sm
    >>> data = sm.datasets.longley.load()
    >>> data.exog = sm.add_constant(data.exog)
    >>> ols_results = sm.OLS(data.endog, data.exog).results
    >>> print ols_results.summary()
    ...

    Notes
    -----
    conf_int calculated from normal dist.
    """
    import time as time



    #TODO Make sure all self.model.__class__.__name__ are listed
    model_types = {'OLS' : 'Ordinary least squares',
                   'GLS' : 'Generalized least squares',
                   'GLSAR' : 'Generalized least squares with AR(p)',
                   'WLS' : 'Weigthed least squares',
                   'RLM' : 'Robust linear model',
                   'GLM' : 'Generalized linear model'
                   }
    model_methods = {'OLS' : 'Least Squares',
                   'GLS' : 'Least Squares',
                   'GLSAR' : 'Least Squares',
                   'WLS' : 'Least Squares',
                   'RLM' : '?',
                   'GLM' : '?'
                   }
    if title==0:
        title = model_types[self.model.__class__.__name__]
    if yname is None:
        try:
            yname = self.model.endog_names
        except AttributeError:
            yname = 'y'
    if xname is None:
        try:
            xname = self.model.exog_names
        except AttributeError:
            xname = ['var_%d' % i for i in range(len(self.params))]
    time_now = time.localtime()
    time_of_day = [time.strftime("%H:%M:%S", time_now)]
    date = time.strftime("%a, %d %b %Y", time_now)
    modeltype = self.model.__class__.__name__
    #dist_family = self.model.family.__class__.__name__
    nobs = self.nobs
    df_model = self.df_model
    df_resid = self.df_resid

    #General part of the summary table, Applicable to all? models
    #------------------------------------------------------------
    #TODO: define this generically, overwrite in model classes
    #replace definition of stubs data by single list
    #e.g.
#.........这里部分代码省略.........

    def summary(self):
        """
        Constructs a summary of the results from a fit model.

        Returns
        -------
        summary : Summary instance
            Object that contains tables and facilitated export to text, html or
            latex
        """
        # Summary layout
        # 1. Overall information
        # 2. Mean parameters
        # 3. Volatility parameters
        # 4. Distribution parameters
        # 5. Notes

        model = self.model
        model_name = model.name + ' - ' + model.volatility.name

        # Summary Header
        top_left = [('Dep. Variable:', self._dep_name),
                    ('Mean Model:', model.name),
                    ('Vol Model:', model.volatility.name),
                    ('Distribution:', model.distribution.name),
                    ('Method:', 'User-specified Parameters'),
                    ('', ''),
                    ('Date:', self._datetime.strftime('%a, %b %d %Y')),
                    ('Time:', self._datetime.strftime('%H:%M:%S'))]

        top_right = [('R-squared:', '--'),
                     ('Adj. R-squared:', '--'),
                     ('Log-Likelihood:', '%#10.6g' % self.loglikelihood),
                     ('AIC:', '%#10.6g' % self.aic),
                     ('BIC:', '%#10.6g' % self.bic),
                     ('No. Observations:', self._nobs),
                     ('', ''),
                     ('', ''),]

        title = model_name + ' Model Results'
        stubs = []
        vals = []
        for stub, val in top_left:
            stubs.append(stub)
            vals.append([val])
        table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)

        # create summary table instance
        smry = Summary()
        # Top Table
        # Parameter table
        fmt = fmt_2cols
        fmt['data_fmts'][1] = '%18s'

        top_right = [('%-21s' % ('  ' + k), v) for k, v in top_right]
        stubs = []
        vals = []
        for stub, val in top_right:
            stubs.append(stub)
            vals.append([val])
        table.extend_right(SimpleTable(vals, stubs=stubs))
        smry.tables.append(table)

        stubs = self._names
        header = ['coef']
        vals = (self.params,)
        formats = [(10, 4)]
        pos = 0
        param_table_data = []
        for _ in range(len(vals[0])):
            row = []
            for i, val in enumerate(vals):
                if isinstance(val[pos], np.float64):
                    converted = format_float_fixed(val[pos], *formats[i])
                else:
                    converted = val[pos]
                row.append(converted)
            pos += 1
            param_table_data.append(row)

        mc = self.model.num_params
        vc = self.model.volatility.num_params
        dc = self.model.distribution.num_params
        counts = (mc, vc, dc)
        titles = ('Mean Model', 'Volatility Model', 'Distribution')
        total = 0
        for title, count in zip(titles, counts):
            if count == 0:
                continue

            table_data = param_table_data[total:total + count]
            table_stubs = stubs[total:total + count]
            total += count
            table = SimpleTable(table_data,
                                stubs=table_stubs,
                                txt_fmt=fmt_params,
                                headers=header, title=title)
            smry.tables.append(table)

        extra_text = ('Results generated with user-specified parameters.',
#.........这里部分代码省略.........

    def summary(self):
        """
        Constructs a summary of the results from a fit model.

        Returns
        -------
        summary : Summary instance
            Object that contains tables and facilitated export to text, html or
            latex
        """
        # Summary layout
        # 1. Overall information
        # 2. Mean parameters
        # 3. Volatility parameters
        # 4. Distribution parameters
        # 5. Notes

        model = self.model
        model_name = model.name + " - " + model.volatility.name

        # Summary Header
        top_left = [
            ("Dep. Variable:", self._dep_name),
            ("Mean Model:", model.name),
            ("Vol Model:", model.volatility.name),
            ("Distribution:", model.distribution.name),
            ("Method:", "User-specified Parameters"),
            ("", ""),
            ("Date:", self._datetime.strftime("%a, %b %d %Y")),
            ("Time:", self._datetime.strftime("%H:%M:%S")),
        ]

        top_right = [
            ("R-squared:", "--"),
            ("Adj. R-squared:", "--"),
            ("Log-Likelihood:", "%#10.6g" % self.loglikelihood),
            ("AIC:", "%#10.6g" % self.aic),
            ("BIC:", "%#10.6g" % self.bic),
            ("No. Observations:", self._nobs),
            ("", ""),
            ("", ""),
        ]

        title = model_name + " Model Results"
        stubs = []
        vals = []
        for stub, val in top_left:
            stubs.append(stub)
            vals.append([val])
        table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)

        # create summary table instance
        smry = Summary()
        # Top Table
        # Parameter table
        fmt = fmt_2cols
        fmt["data_fmts"][1] = "%18s"

        top_right = [("%-21s" % ("  " + k), v) for k, v in top_right]
        stubs = []
        vals = []
        for stub, val in top_right:
            stubs.append(stub)
            vals.append([val])
        table.extend_right(SimpleTable(vals, stubs=stubs))
        smry.tables.append(table)

        stubs = self._names
        header = ["coef"]
        vals = (self.params,)
        formats = [(10, 4)]
        pos = 0
        param_table_data = []
        for _ in range(len(vals[0])):
            row = []
            for i, val in enumerate(vals):
                if isinstance(val[pos], np.float64):
                    converted = format_float_fixed(val[pos], *formats[i])
                else:
                    converted = val[pos]
                row.append(converted)
            pos += 1
            param_table_data.append(row)

        mc = self.model.num_params
        vc = self.model.volatility.num_params
        dc = self.model.distribution.num_params
        counts = (mc, vc, dc)
        titles = ("Mean Model", "Volatility Model", "Distribution")
        total = 0
        for title, count in zip(titles, counts):
            if count == 0:
                continue

            table_data = param_table_data[total : total + count]
            table_stubs = stubs[total : total + count]
            total += count
            table = SimpleTable(table_data, stubs=table_stubs, txt_fmt=fmt_params, headers=header, title=title)
            smry.tables.append(table)

#.........这里部分代码省略.........