Getting getting
----------------

Begin by importing the pysoplot module.

.. code-block:: python

   import pysoplot

A test data set can be accessed from the ``pysoplot.data`` module.

.. code-block:: python

   dp = pysoplot.data.LA0708

The analytical uncertainties on this data set are given at the :math:`2\sigma` level. As a general rule, functions in pysoplot expect uncertainties to be given as :math:`1\sigma` absolute, so we will need to transform these before continuing. 

.. code-block:: python

   dp = pysoplot.transform.dp_errors(dp, 'abs2s')

Now that these data point uncertainties are in the correct form, we can fit a linear regression. by setting the ``plot`` argument to ``True``, we have told the function to also compile a plot of the data points and regression fit. 

.. code-block:: python

   fit = pysoplot.regression.robust_fit(*dp, plot=True, diagram='tw')

This function returns a dictionary containing the regression fitting results and the plot. We can print the regression results and show the plot

.. code-block:: python

   pysoplot.misc.print_result(fit, 'Regression results')
   fit['fig'].show()

Now that we have fitted a regression line, we can compute a concordia intercept age

.. code-block:: python

   tw = pysoplot.upb.concint_age(fit, method='Powell')


More coming soon...