PySRRegressor has many options for controlling a symbolic regression search.
+Let's look at them below.
PARAMSKEY
+fit(X, y, Xresampled=None, weights=None, variable_names=None, X_units=None, y_units=None)
+
+¶Search for equations to fit the dataset and store them in self.equations_.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
X |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Training data of shape (n_samples, n_features). + |
+ + required + | +
y |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Target values of shape (n_samples,) or (n_samples, n_targets). +Will be cast to X's dtype if necessary. + |
+ + required + | +
Xresampled |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Resampled training data, of shape (n_resampled, n_features),
+to generate a denoised data on. This
+will be used as the training data, rather than |
+
+ None
+ |
+
weights |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Weight array of the same shape as |
+
+ None
+ |
+
variable_names |
+
+ list[str]
+ |
+
+
+
+ A list of names for the variables, rather than "x0", "x1", etc.
+If |
+
+ None
+ |
+
X_units |
+
+ list[str]
+ |
+
+
+
+ A list of units for each variable in |
+
+ None
+ |
+
y_units |
+
+ str | list[str]
+ |
+
+
+
+ Similar to |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
self |
+ object
+ |
+
+
+
+ Fitted estimator. + |
+
pysr/sr.py1737 +1738 +1739 +1740 +1741 +1742 +1743 +1744 +1745 +1746 +1747 +1748 +1749 +1750 +1751 +1752 +1753 +1754 +1755 +1756 +1757 +1758 +1759 +1760 +1761 +1762 +1763 +1764 +1765 +1766 +1767 +1768 +1769 +1770 +1771 +1772 +1773 +1774 +1775 +1776 +1777 +1778 +1779 +1780 +1781 +1782 +1783 +1784 +1785 +1786 +1787 +1788 +1789 +1790 +1791 +1792 +1793 +1794 +1795 +1796 +1797 +1798 +1799 +1800 +1801 +1802 +1803 +1804 +1805 +1806 +1807 +1808 +1809 +1810 +1811 +1812 +1813 +1814 +1815 +1816 +1817 +1818 +1819 +1820 +1821 +1822 +1823 +1824 +1825 +1826 +1827 +1828 +1829 +1830 +1831 +1832 +1833 +1834 +1835 +1836 +1837 +1838 +1839 +1840 +1841 +1842 +1843 +1844 +1845 +1846 +1847 +1848 +1849 +1850 +1851 +1852 +1853 +1854 +1855 +1856 +1857 +1858 +1859 +1860 +1861 +1862 +1863 +1864 +1865 +1866 +1867 +1868 +1869 +1870 +1871 +1872 +1873 +1874 +1875 +1876 +1877 +1878 +1879 +1880 +1881 +1882 +1883 +1884 | |
predict(X, index=None)
+
+¶Predict y from input X using the equation chosen by model_selection.
You may see what equation is used by printing this object. X should +have the same columns as the training data.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
X |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Training data of shape |
+ + required + | +
index |
+
+ int | list[int]
+ |
+
+
+
+ If you want to compute the output of an expression using a
+particular row of |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
y_predicted |
+ ndarray of shape (n_samples, nout_)
+ |
+
+
+
+ Values predicted by substituting |
+
Raises:
+| Type | +Description | +
|---|---|
+ ValueError
+ |
+
+
+
+ Raises if the |
+
pysr/sr.py1905 +1906 +1907 +1908 +1909 +1910 +1911 +1912 +1913 +1914 +1915 +1916 +1917 +1918 +1919 +1920 +1921 +1922 +1923 +1924 +1925 +1926 +1927 +1928 +1929 +1930 +1931 +1932 +1933 +1934 +1935 +1936 +1937 +1938 +1939 +1940 +1941 +1942 +1943 +1944 +1945 +1946 +1947 +1948 +1949 +1950 +1951 +1952 +1953 +1954 +1955 +1956 +1957 +1958 +1959 +1960 +1961 +1962 +1963 +1964 +1965 +1966 +1967 +1968 +1969 +1970 +1971 +1972 +1973 +1974 +1975 +1976 | |
from_file(equation_file, *, binary_operators=None, unary_operators=None, n_features_in=None, feature_names_in=None, selection_mask=None, nout=1, **pysr_kwargs)
+
+
+ classmethod
+
+
+¶Create a model from a saved model checkpoint or equation file.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
equation_file |
+
+ str
+ |
+
+
+
+ Path to a pickle file containing a saved model, or a csv file +containing equations. + |
+ + required + | +
binary_operators |
+
+ list[str]
+ |
+
+
+
+ The same binary operators used when creating the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
unary_operators |
+
+ list[str]
+ |
+
+
+
+ The same unary operators used when creating the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
n_features_in |
+
+ int
+ |
+
+
+
+ Number of features passed to the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
feature_names_in |
+
+ list[str]
+ |
+
+
+
+ Names of the features passed to the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
selection_mask |
+
+ list[bool]
+ |
+
+
+
+ If using select_k_features, you must pass |
+
+ None
+ |
+
nout |
+
+ int
+ |
+
+
+
+ Number of outputs of the model.
+Not needed if loading from a pickle file.
+Default is |
+
+ 1
+ |
+
**pysr_kwargs |
+
+ dict
+ |
+
+
+
+ Any other keyword arguments to initialize the PySRRegressor object. +These will overwrite those stored in the pickle file. +Not needed if loading from a pickle file. + |
+
+ {}
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
model |
+ PySRRegressor
+ |
+
+
+
+ The model with fitted equations. + |
+
pysr/sr.py865 +866 +867 +868 +869 +870 +871 +872 +873 +874 +875 +876 +877 +878 +879 +880 +881 +882 +883 +884 +885 +886 +887 +888 +889 +890 +891 +892 +893 +894 +895 +896 +897 +898 +899 +900 +901 +902 +903 +904 +905 +906 +907 +908 +909 +910 +911 +912 +913 +914 +915 +916 +917 +918 +919 +920 +921 +922 +923 +924 +925 +926 +927 +928 +929 +930 +931 +932 +933 +934 +935 +936 +937 +938 +939 +940 +941 +942 +943 +944 +945 +946 +947 +948 +949 +950 +951 +952 +953 +954 +955 +956 +957 +958 +959 +960 +961 +962 +963 +964 +965 +966 +967 +968 +969 +970 +971 +972 +973 +974 +975 +976 | |
sympy(index=None)
+
+¶Return sympy representation of the equation(s) chosen by model_selection.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ str, list[str] of length nout_
+ |
+
+
+
+ SymPy representation of the best equation. + |
+
pysr/sr.pylatex(index=None, precision=3)
+
+¶Return latex representation of the equation(s) chosen by model_selection.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
precision |
+
+ int
+ |
+
+
+
+ The number of significant figures shown in the LaTeX
+representation.
+Default is |
+
+ 3
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ str or list[str] of length nout_
+ |
+
+
+
+ LaTeX expression of the best equation. + |
+
pysr/sr.pypytorch(index=None)
+
+¶Return pytorch representation of the equation(s) chosen by model_selection.
Each equation (multiple given if there are multiple outputs) is a PyTorch module
+containing the parameters as trainable attributes. You can use the module like
+any other PyTorch module: module(X), where X is a tensor with the same
+column ordering as trained with.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ Module
+ |
+
+
+
+ PyTorch module representing the expression. + |
+
pysr/sr.pyjax(index=None)
+
+¶Return jax representation of the equation(s) chosen by model_selection.
Each equation (multiple given if there are multiple outputs) is a dictionary
+containing {"callable": func, "parameters": params}. To call func, pass
+func(X, params). This function is differentiable using jax.grad.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ dict[str, Any]
+ |
+
+
+
+ Dictionary of callable jax function in "callable" key, +and jax array of parameters as "parameters" key. + |
+
pysr/sr.pylatex_table(indices=None, precision=3, columns=['equation', 'complexity', 'loss', 'score'])
+
+¶Create a LaTeX/booktabs table for all, or some, of the equations.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
indices |
+
+ list[int] | list[list[int]]
+ |
+
+
+
+ If you wish to select a particular subset of equations from
+ |
+
+ None
+ |
+
precision |
+
+ int
+ |
+
+
+
+ The number of significant figures shown in the LaTeX
+representations.
+Default is |
+
+ 3
+ |
+
columns |
+
+ list[str]
+ |
+
+
+
+ Which columns to include in the table.
+Default is |
+
+ ['equation', 'complexity', 'loss', 'score']
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
latex_table_str |
+ str
+ |
+
+
+
+ A string that will render a table in LaTeX of the equations. + |
+
pysr/sr.py2275 +2276 +2277 +2278 +2279 +2280 +2281 +2282 +2283 +2284 +2285 +2286 +2287 +2288 +2289 +2290 +2291 +2292 +2293 +2294 +2295 +2296 +2297 +2298 +2299 +2300 +2301 +2302 +2303 +2304 +2305 +2306 +2307 +2308 +2309 +2310 +2311 +2312 +2313 +2314 +2315 +2316 +2317 +2318 +2319 +2320 +2321 +2322 +2323 +2324 +2325 +2326 +2327 +2328 +2329 +2330 | |
refresh(checkpoint_file=None)
+
+¶Update self.equations_ with any new options passed.
+For example, updating extra_sympy_mappings
+will require a .refresh() to update the equations.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
checkpoint_file |
+
+ str
+ |
+
+
+
+ Path to checkpoint hall of fame file to be loaded.
+The default will use the set |
+
+ None
+ |
+
pysr/sr.pyFunctions for initializing the Julia environment and installing deps.
+ + + +init_julia(julia_project=None, quiet=False, julia_kwargs=None, return_aux=False)
+
+¶Initialize julia binary, turning off compiled modules if needed.
+ +pysr/julia_helpers.py180 +181 +182 +183 +184 +185 +186 +187 +188 +189 +190 +191 +192 +193 +194 +195 +196 +197 +198 +199 +200 +201 +202 +203 +204 +205 +206 +207 +208 +209 +210 +211 +212 +213 +214 +215 +216 +217 +218 +219 +220 +221 +222 +223 +224 +225 +226 +227 +228 +229 +230 +231 +232 +233 +234 +235 +236 +237 +238 +239 +240 +241 +242 +243 +244 +245 +246 +247 +248 +249 +250 +251 +252 +253 +254 +255 +256 +257 +258 +259 +260 +261 +262 +263 +264 +265 +266 | |
install(julia_project=None, quiet=False, precompile=None)
+
+¶Install PyCall.jl and all required dependencies for SymbolicRegression.jl.
+Also updates the local Julia registry.
+ +pysr/julia_helpers.py69 + 70 + 71 + 72 + 73 + 74 + 75 + 76 + 77 + 78 + 79 + 80 + 81 + 82 + 83 + 84 + 85 + 86 + 87 + 88 + 89 + 90 + 91 + 92 + 93 + 94 + 95 + 96 + 97 + 98 + 99 +100 +101 +102 +103 +104 +105 +106 +107 +108 +109 +110 +111 +112 +113 +114 +115 +116 +117 +118 +119 +120 +121 +122 +123 +124 +125 +126 +127 +128 +129 +130 | |
Functions to help export PySR equations to LaTeX.
+ + + +generate_table_environment(columns=['equation', 'complexity', 'loss'])
+
+¶pysr/export_latex.pysympy2jax(expression, symbols_in, selection=None, extra_jax_mappings=None)
+
+¶Returns a function f and its parameters; +the function takes an input matrix, and a list of arguments: + f(X, parameters) +where the parameters appear in the JAX equation.
+Let's create a function in SymPy:
+```python
+x, y = symbols('x y')
+cosx = 1.0 * sympy.cos(x) + 3.2 * y
+```
+Let's get the JAX version. We pass the equation, and
+the symbols required.
+```python
+f, params = sympy2jax(cosx, [x, y])
+```
+The order you supply the symbols is the same order
+you should supply the features when calling
+the function `f` (shape `[nrows, nfeatures]`).
+In this case, features=2 for x and y.
+The `params` in this case will be
+`jnp.array([1.0, 3.2])`. You pass these parameters
+when calling the function, which will let you change them
+and take gradients.
+
+Let's generate some JAX data to pass:
+```python
+key = random.PRNGKey(0)
+X = random.normal(key, (10, 2))
+```
+
+We can call the function with:
+```python
+f(X, params)
+
+#> DeviceArray([-2.6080756 , 0.72633684, -6.7557726 , -0.2963162 ,
+# 6.6014843 , 5.032483 , -0.810931 , 4.2520013 ,
+# 3.5427954 , -2.7479894 ], dtype=float32)
+```
+
+We can take gradients with respect
+to the parameters for each row with JAX
+gradient parameters now:
+```python
+jac_f = jax.jacobian(f, argnums=1)
+jac_f(X, params)
+
+#> DeviceArray([[ 0.49364874, -0.9692889 ],
+# [ 0.8283714 , -0.0318858 ],
+# [-0.7447336 , -1.8784496 ],
+# [ 0.70755106, -0.3137085 ],
+# [ 0.944834 , 1.767703 ],
+# [ 0.51673377, 1.4111717 ],
+# [ 0.87347716, -0.52637756],
+# [ 0.8760679 , 1.0549792 ],
+# [ 0.9961824 , 0.79581654],
+# [-0.88465923, -0.5822907 ]], dtype=float32)
+```
+
+We can also JIT-compile our function:
+```python
+compiled_f = jax.jit(f)
+compiled_f(X, params)
+
+#> DeviceArray([-2.6080756 , 0.72633684, -6.7557726 , -0.2963162 ,
+# 6.6014843 , 5.032483 , -0.810931 , 4.2520013 ,
+# 3.5427954 , -2.7479894 ], dtype=float32)
+```
+pysr/export_jax.py111 +112 +113 +114 +115 +116 +117 +118 +119 +120 +121 +122 +123 +124 +125 +126 +127 +128 +129 +130 +131 +132 +133 +134 +135 +136 +137 +138 +139 +140 +141 +142 +143 +144 +145 +146 +147 +148 +149 +150 +151 +152 +153 +154 +155 +156 +157 +158 +159 +160 +161 +162 +163 +164 +165 +166 +167 +168 +169 +170 +171 +172 +173 +174 +175 +176 +177 +178 +179 +180 +181 +182 +183 +184 +185 +186 +187 +188 +189 +190 +191 +192 +193 +194 +195 +196 +197 +198 +199 +200 +201 | |
sympy2jaxtext(expr, parameters, symbols_in, extra_jax_mappings=None)
+
+¶pysr/export_jax.pysympy2torch(expression, symbols_in, selection=None, extra_torch_mappings=None)
+
+¶Returns a module for a given sympy expression with trainable parameters;
+This function will assume the input to the module is a matrix X, where
+ each column corresponds to each symbol you pass in symbols_in.
pysr/export_torch.pyPySRRegressor has many options for controlling a symbolic regression search.
+Let's look at them below.
binary_operators
List of strings for binary operators used in the search. +See the operators page +for more details.
+Default: ["+", "-", "*", "/"]
unary_operators
Operators which only take a single scalar as input.
+For example, "cos" or "exp".
Default: None
maxsize
Max complexity of an equation.
+Default: 20
maxdepth
Max depth of an equation. You can use both maxsize and
+maxdepth. maxdepth is by default not used.
Default: None
niterations
Number of iterations of the algorithm to run. The best +equations are printed and migrate between populations at the +end of each iteration.
+Default: 40
populations
Number of populations running.
+Default: 15
population_size
Number of individuals in each population.
+Default: 33
ncyclesperiteration
Number of total mutations to run, per 10 samples of the +population, per iteration.
+Default: 550
loss
String of Julia code specifying an elementwise loss function.
+Can either be a loss from LossFunctions.jl, or your own loss
+written as a function. Examples of custom written losses include:
+myloss(x, y) = abs(x-y) for non-weighted, or
+myloss(x, y, w) = w*abs(x-y) for weighted.
+The included losses include:
+Regression: LPDistLoss{P}(), L1DistLoss(),
+L2DistLoss() (mean square), LogitDistLoss(),
+HuberLoss(d), L1EpsilonInsLoss(ϵ), L2EpsilonInsLoss(ϵ),
+PeriodicLoss(c), QuantileLoss(τ).
+Classification: ZeroOneLoss(), PerceptronLoss(),
+L1HingeLoss(), SmoothedL1HingeLoss(γ),
+ModifiedHuberLoss(), L2MarginLoss(), ExpLoss(),
+SigmoidLoss(), DWDMarginLoss(q).
Default: "L2DistLoss()"
full_objective
Alternatively, you can specify the full objective function as
+a snippet of Julia code, including any sort of custom evaluation
+(including symbolic manipulations beforehand), and any sort
+of loss function or regularizations. The default full_objective
+used in SymbolicRegression.jl is roughly equal to:
+
function eval_loss(tree, dataset::Dataset{T,L}, options)::L where {T,L}
+ prediction, flag = eval_tree_array(tree, dataset.X, options)
+ if !flag
+ return L(Inf)
+ end
+ return sum((prediction .- dataset.y) .^ 2) / dataset.n
+end
+prediction and dataset.y are 1D arrays of length dataset.n.
+If using batching, then you should add an
+idx argument to the function, which is nothing
+for non-batched, and a 1D array of indices for batched.
+Default: None
model_selection
Model selection criterion when selecting a final expression from
+the list of best expression at each complexity.
+Can be 'accuracy', 'best', or 'score'.
+'accuracy' selects the candidate model with the lowest loss
+(highest accuracy).
+'score' selects the candidate model with the highest score.
+Score is defined as the negated derivative of the log-loss with
+respect to complexity - if an expression has a much better
+loss at a slightly higher complexity, it is preferred.
+'best' selects the candidate model with the highest score
+among expressions with a loss better than at least 1.5x the
+most accurate model.
Default: 'best'
dimensional_constraint_penalty
Additive penalty for if dimensional analysis of an expression fails.
+By default, this is 1000.0.
parsimony
Multiplicative factor for how much to punish complexity.
+Default: 0.0032
constraints
Dictionary of int (unary) or 2-tuples (binary), this enforces
+maxsize constraints on the individual arguments of operators.
+E.g., 'pow': (-1, 1) says that power laws can have any
+complexity left argument, but only 1 complexity in the right
+argument. Use this to force more interpretable solutions.
Default: None
nested_constraints
Specifies how many times a combination of operators can be
+nested. For example, {"sin": {"cos": 0}}, "cos": {"cos": 2}}
+specifies that cos may never appear within a sin, but sin
+can be nested with itself an unlimited number of times. The
+second term specifies that cos can be nested up to 2 times
+within a cos, so that cos(cos(cos(x))) is allowed
+(as well as any combination of + or - within it), but
+cos(cos(cos(cos(x)))) is not allowed. When an operator is not
+specified, it is assumed that it can be nested an unlimited
+number of times. This requires that there is no operator which
+is used both in the unary operators and the binary operators
+(e.g., - could be both subtract, and negation). For binary
+operators, you only need to provide a single number: both
+arguments are treated the same way, and the max of each
+argument is constrained.
Default: None
complexity_of_operators
If you would like to use a complexity other than 1 for an
+operator, specify the complexity here. For example,
+{"sin": 2, "+": 1} would give a complexity of 2 for each use
+of the sin operator, and a complexity of 1 for each use of
+the + operator (which is the default). You may specify real
+numbers for a complexity, and the total complexity of a tree
+will be rounded to the nearest integer after computing.
Default: None
complexity_of_constants
Complexity of constants.
+Default: 1
complexity_of_variables
Complexity of variables.
+Default: 1
warmup_maxsize_by
Whether to slowly increase max size from a small number up to +the maxsize (if greater than 0). If greater than 0, says the +fraction of training time at which the current maxsize will +reach the user-passed maxsize.
+Default: 0.0
use_frequency
Whether to measure the frequency of complexities, and use that +instead of parsimony to explore equation space. Will naturally +find equations of all complexities.
+Default: True
use_frequency_in_tournament
Whether to use the frequency mentioned above in the tournament, +rather than just the simulated annealing.
+Default: True
adaptive_parsimony_scaling
If the adaptive parsimony strategy (use_frequency and
+use_frequency_in_tournament), this is how much to (exponentially)
+weight the contribution. If you find that the search is only optimizing
+the most complex expressions while the simpler expressions remain stagnant,
+you should increase this value.
Default: 20.0
should_simplify
Whether to use algebraic simplification in the search. Note that only +a few simple rules are implemented.
+Default: True
weight_add_node
Relative likelihood for mutation to add a node.
+Default: 0.79
weight_insert_node
Relative likelihood for mutation to insert a node.
+Default: 5.1
weight_delete_node
Relative likelihood for mutation to delete a node.
+Default: 1.7
weight_do_nothing
Relative likelihood for mutation to leave the individual.
+Default: 0.21
weight_mutate_constant
Relative likelihood for mutation to change the constant slightly +in a random direction.
+Default: 0.048
weight_mutate_operator
Relative likelihood for mutation to swap an operator.
+Default: 0.47
weight_randomize
Relative likelihood for mutation to completely delete and then +randomly generate the equation
+Default: 0.00023
weight_simplify
Relative likelihood for mutation to simplify constant parts by evaluation
+Default: 0.0020
weight_optimize
Constant optimization can also be performed as a mutation, in addition to
+the normal strategy controlled by optimize_probability which happens
+every iteration. Using it as a mutation is useful if you want to use
+a large ncyclesperiteration, and may not optimize very often.
Default: 0.0
crossover_probability
Absolute probability of crossover-type genetic operation, instead of a mutation.
+Default: 0.066
annealing
Whether to use annealing.
+Default: False
alpha
Initial temperature for simulated annealing
+(requires annealing to be True).
Default: 0.1
perturbation_factor
Constants are perturbed by a max factor of +(perturbation_factor*T + 1). Either multiplied by this or +divided by this.
+Default: 0.076
skip_mutation_failures
Whether to skip mutation and crossover failures, rather than +simply re-sampling the current member.
+Default: True
tournament_selection_n
Number of expressions to consider in each tournament.
+Default: 10
tournament_selection_p
Probability of selecting the best expression in each +tournament. The probability will decay as p*(1-p)^n for other +expressions, sorted by loss.
+Default: 0.86
optimizer_algorithm
Optimization scheme to use for optimizing constants. Can currently
+be NelderMead or BFGS.
Default: "BFGS"
optimizer_nrestarts
Number of time to restart the constants optimization process with +different initial conditions.
+Default: 2
optimize_probability
Probability of optimizing the constants during a single iteration of +the evolutionary algorithm.
+Default: 0.14
optimizer_iterations
Number of iterations that the constants optimizer can take.
+Default: 8
should_optimize_constants
Whether to numerically optimize constants (Nelder-Mead/Newton) +at the end of each iteration.
+Default: True
fraction_replaced
How much of population to replace with migrating equations from +other populations.
+Default: 0.000364
fraction_replaced_hof
How much of population to replace with migrating equations from +hall of fame.
+Default: 0.035
migration
Whether to migrate.
+Default: True
hof_migration
Whether to have the hall of fame migrate.
+Default: True
topn
How many top individuals migrate from each population.
+Default: 12
denoise
Whether to use a Gaussian Process to denoise the data before +inputting to PySR. Can help PySR fit noisy data.
+Default: False
select_k_features
Whether to run feature selection in Python using random forests, +before passing to the symbolic regression code. None means no +feature selection; an int means select that many features.
+Default: None
max_evals
Limits the total number of evaluations of expressions to +this number.
+Default: None
timeout_in_seconds
Make the search return early once this many seconds have passed.
+Default: None
early_stop_condition
Stop the search early if this loss is reached. You may also
+pass a string containing a Julia function which
+takes a loss and complexity as input, for example:
+"f(loss, complexity) = (loss < 0.1) && (complexity < 10)".
Default: None
procs
Number of processes (=number of populations running).
+Default: cpu_count()
multithreading
Use multithreading instead of distributed backend. +Using procs=0 will turn off both.
+Default: True
cluster_manager
For distributed computing, this sets the job queue system. Set
+to one of "slurm", "pbs", "lsf", "sge", "qrsh", "scyld", or
+"htc". If set to one of these, PySR will run in distributed
+mode, and use procs to figure out how many processes to launch.
Default: None
batching
Whether to compare population members on small batches during +evolution. Still uses full dataset for comparing against hall +of fame.
+Default: False
batch_size
The amount of data to use if doing batching.
+Default: 50
precision
What precision to use for the data. By default this is 32
+(float32), but you can select 64 or 16 as well, giving
+you 64 or 16 bits of floating point precision, respectively.
+If you pass complex data, the corresponding complex precision
+will be used (i.e., 64 for complex128, 32 for complex64).
Default: 32
fast_cycle
Batch over population subsamples. This is a slightly different +algorithm than regularized evolution, but does cycles 15% +faster. May be algorithmically less efficient.
+Default: False
turbo
(Experimental) Whether to use LoopVectorization.jl to speed up the +search evaluation. Certain operators may not be supported. +Does not support 16-bit precision floats.
+Default: False
enable_autodiff
Whether to create derivative versions of operators for automatic +differentiation. This is only necessary if you wish to compute +the gradients of an expression within a custom loss function.
+Default: False
random_state
Pass an int for reproducible results across multiple function calls.
+See :term:Glossary <random_state>.
Default: None
deterministic
Make a PySR search give the same result every run.
+To use this, you must turn off parallelism
+(with procs=0, multithreading=False),
+and set random_state to a fixed seed.
Default: False
warm_start
Tells fit to continue from where the last call to fit finished. +If false, each call to fit will be fresh, overwriting previous results.
+Default: False
verbosity
What verbosity level to use. 0 means minimal print statements.
+Default: 1
update_verbosity
What verbosity level to use for package updates.
+Will take value of verbosity if not given.
Default: None
print_precision
How many significant digits to print for floats.
+Default: 5
progress
Whether to use a progress bar instead of printing to stdout.
+Default: True
temp_equation_file
Whether to put the hall of fame file in the temp directory.
+Deletion is then controlled with the delete_tempfiles
+parameter.
Default: False
tempdir
directory for the temporary files.
+Default: None
delete_tempfiles
Whether to delete the temporary files after finishing.
+Default: True
julia_project
A Julia environment location containing a Project.toml +(and potentially the source code for SymbolicRegression.jl). +Default gives the Python package directory, where a +Project.toml file should be present from the install.
+update
Whether to automatically update Julia packages when fit is called.
+You should make sure that PySR is up-to-date itself first, as
+the packaged Julia packages may not necessarily include all
+updated dependencies.
Default: False
julia_kwargs
Keyword arguments to pass to julia.core.Julia(...) to initialize
+the Julia runtime. The default, when None, is to set threads equal
+to procs, and optimize to 3.
Default: None
equation_file
Where to save the files (.csv extension).
+Default: None
output_jax_format
Whether to create a 'jax_format' column in the output, +containing jax-callable functions and the default parameters in +a jax array.
+Default: False
output_torch_format
Whether to create a 'torch_format' column in the output, +containing a torch module with trainable parameters.
+Default: False
extra_sympy_mappings
Provides mappings between custom binary_operators or
+unary_operators defined in julia strings, to those same
+operators defined in sympy.
+E.G if unary_operators=["inv(x)=1/x"], then for the fitted
+model to be export to sympy, extra_sympy_mappings
+would be {"inv": lambda x: 1/x}.
Default: None
extra_torch_mappings
The same as extra_jax_mappings but for model export
+to pytorch. Note that the dictionary keys should be callable
+pytorch expressions.
+For example: extra_torch_mappings={sympy.sin: torch.sin}.
Default: None
extra_jax_mappings
Similar to extra_sympy_mappings but for model export
+to jax. The dictionary maps sympy functions to jax functions.
+For example: extra_jax_mappings={sympy.sin: "jnp.sin"} maps
+the sympy.sin function to the equivalent jax expression jnp.sin.
Default: None
fit(X, y, Xresampled=None, weights=None, variable_names=None, X_units=None, y_units=None)
+
+¶Search for equations to fit the dataset and store them in self.equations_.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
X |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Training data of shape (n_samples, n_features). + |
+ + required + | +
y |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Target values of shape (n_samples,) or (n_samples, n_targets). +Will be cast to X's dtype if necessary. + |
+ + required + | +
Xresampled |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Resampled training data, of shape (n_resampled, n_features),
+to generate a denoised data on. This
+will be used as the training data, rather than |
+
+ None
+ |
+
weights |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Weight array of the same shape as |
+
+ None
+ |
+
variable_names |
+
+ list[str]
+ |
+
+
+
+ A list of names for the variables, rather than "x0", "x1", etc.
+If |
+
+ None
+ |
+
X_units |
+
+ list[str]
+ |
+
+
+
+ A list of units for each variable in |
+
+ None
+ |
+
y_units |
+
+ str | list[str]
+ |
+
+
+
+ Similar to |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
self |
+ object
+ |
+
+
+
+ Fitted estimator. + |
+
pysr/sr.py1737 +1738 +1739 +1740 +1741 +1742 +1743 +1744 +1745 +1746 +1747 +1748 +1749 +1750 +1751 +1752 +1753 +1754 +1755 +1756 +1757 +1758 +1759 +1760 +1761 +1762 +1763 +1764 +1765 +1766 +1767 +1768 +1769 +1770 +1771 +1772 +1773 +1774 +1775 +1776 +1777 +1778 +1779 +1780 +1781 +1782 +1783 +1784 +1785 +1786 +1787 +1788 +1789 +1790 +1791 +1792 +1793 +1794 +1795 +1796 +1797 +1798 +1799 +1800 +1801 +1802 +1803 +1804 +1805 +1806 +1807 +1808 +1809 +1810 +1811 +1812 +1813 +1814 +1815 +1816 +1817 +1818 +1819 +1820 +1821 +1822 +1823 +1824 +1825 +1826 +1827 +1828 +1829 +1830 +1831 +1832 +1833 +1834 +1835 +1836 +1837 +1838 +1839 +1840 +1841 +1842 +1843 +1844 +1845 +1846 +1847 +1848 +1849 +1850 +1851 +1852 +1853 +1854 +1855 +1856 +1857 +1858 +1859 +1860 +1861 +1862 +1863 +1864 +1865 +1866 +1867 +1868 +1869 +1870 +1871 +1872 +1873 +1874 +1875 +1876 +1877 +1878 +1879 +1880 +1881 +1882 +1883 +1884 | |
predict(X, index=None)
+
+¶Predict y from input X using the equation chosen by model_selection.
You may see what equation is used by printing this object. X should +have the same columns as the training data.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
X |
+
+ ndarray | DataFrame
+ |
+
+
+
+ Training data of shape |
+ + required + | +
index |
+
+ int | list[int]
+ |
+
+
+
+ If you want to compute the output of an expression using a
+particular row of |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
y_predicted |
+ ndarray of shape (n_samples, nout_)
+ |
+
+
+
+ Values predicted by substituting |
+
Raises:
+| Type | +Description | +
|---|---|
+ ValueError
+ |
+
+
+
+ Raises if the |
+
pysr/sr.py1905 +1906 +1907 +1908 +1909 +1910 +1911 +1912 +1913 +1914 +1915 +1916 +1917 +1918 +1919 +1920 +1921 +1922 +1923 +1924 +1925 +1926 +1927 +1928 +1929 +1930 +1931 +1932 +1933 +1934 +1935 +1936 +1937 +1938 +1939 +1940 +1941 +1942 +1943 +1944 +1945 +1946 +1947 +1948 +1949 +1950 +1951 +1952 +1953 +1954 +1955 +1956 +1957 +1958 +1959 +1960 +1961 +1962 +1963 +1964 +1965 +1966 +1967 +1968 +1969 +1970 +1971 +1972 +1973 +1974 +1975 +1976 | |
from_file(equation_file, *, binary_operators=None, unary_operators=None, n_features_in=None, feature_names_in=None, selection_mask=None, nout=1, **pysr_kwargs)
+
+
+ classmethod
+
+
+¶Create a model from a saved model checkpoint or equation file.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
equation_file |
+
+ str
+ |
+
+
+
+ Path to a pickle file containing a saved model, or a csv file +containing equations. + |
+ + required + | +
binary_operators |
+
+ list[str]
+ |
+
+
+
+ The same binary operators used when creating the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
unary_operators |
+
+ list[str]
+ |
+
+
+
+ The same unary operators used when creating the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
n_features_in |
+
+ int
+ |
+
+
+
+ Number of features passed to the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
feature_names_in |
+
+ list[str]
+ |
+
+
+
+ Names of the features passed to the model. +Not needed if loading from a pickle file. + |
+
+ None
+ |
+
selection_mask |
+
+ list[bool]
+ |
+
+
+
+ If using select_k_features, you must pass |
+
+ None
+ |
+
nout |
+
+ int
+ |
+
+
+
+ Number of outputs of the model.
+Not needed if loading from a pickle file.
+Default is |
+
+ 1
+ |
+
**pysr_kwargs |
+
+ dict
+ |
+
+
+
+ Any other keyword arguments to initialize the PySRRegressor object. +These will overwrite those stored in the pickle file. +Not needed if loading from a pickle file. + |
+
+ {}
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
model |
+ PySRRegressor
+ |
+
+
+
+ The model with fitted equations. + |
+
pysr/sr.py865 +866 +867 +868 +869 +870 +871 +872 +873 +874 +875 +876 +877 +878 +879 +880 +881 +882 +883 +884 +885 +886 +887 +888 +889 +890 +891 +892 +893 +894 +895 +896 +897 +898 +899 +900 +901 +902 +903 +904 +905 +906 +907 +908 +909 +910 +911 +912 +913 +914 +915 +916 +917 +918 +919 +920 +921 +922 +923 +924 +925 +926 +927 +928 +929 +930 +931 +932 +933 +934 +935 +936 +937 +938 +939 +940 +941 +942 +943 +944 +945 +946 +947 +948 +949 +950 +951 +952 +953 +954 +955 +956 +957 +958 +959 +960 +961 +962 +963 +964 +965 +966 +967 +968 +969 +970 +971 +972 +973 +974 +975 +976 | |
sympy(index=None)
+
+¶Return sympy representation of the equation(s) chosen by model_selection.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ str, list[str] of length nout_
+ |
+
+
+
+ SymPy representation of the best equation. + |
+
pysr/sr.pylatex(index=None, precision=3)
+
+¶Return latex representation of the equation(s) chosen by model_selection.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
precision |
+
+ int
+ |
+
+
+
+ The number of significant figures shown in the LaTeX
+representation.
+Default is |
+
+ 3
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ str or list[str] of length nout_
+ |
+
+
+
+ LaTeX expression of the best equation. + |
+
pysr/sr.pypytorch(index=None)
+
+¶Return pytorch representation of the equation(s) chosen by model_selection.
Each equation (multiple given if there are multiple outputs) is a PyTorch module
+containing the parameters as trainable attributes. You can use the module like
+any other PyTorch module: module(X), where X is a tensor with the same
+column ordering as trained with.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ Module
+ |
+
+
+
+ PyTorch module representing the expression. + |
+
pysr/sr.pyjax(index=None)
+
+¶Return jax representation of the equation(s) chosen by model_selection.
Each equation (multiple given if there are multiple outputs) is a dictionary
+containing {"callable": func, "parameters": params}. To call func, pass
+func(X, params). This function is differentiable using jax.grad.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
index |
+
+ int | list[int]
+ |
+
+
+
+ If you wish to select a particular equation from
+ |
+
+ None
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
best_equation |
+ dict[str, Any]
+ |
+
+
+
+ Dictionary of callable jax function in "callable" key, +and jax array of parameters as "parameters" key. + |
+
pysr/sr.pylatex_table(indices=None, precision=3, columns=['equation', 'complexity', 'loss', 'score'])
+
+¶Create a LaTeX/booktabs table for all, or some, of the equations.
+ + + +Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
indices |
+
+ list[int] | list[list[int]]
+ |
+
+
+
+ If you wish to select a particular subset of equations from
+ |
+
+ None
+ |
+
precision |
+
+ int
+ |
+
+
+
+ The number of significant figures shown in the LaTeX
+representations.
+Default is |
+
+ 3
+ |
+
columns |
+
+ list[str]
+ |
+
+
+
+ Which columns to include in the table.
+Default is |
+
+ ['equation', 'complexity', 'loss', 'score']
+ |
+
Returns:
+| Name | Type | +Description | +
|---|---|---|
latex_table_str |
+ str
+ |
+
+
+
+ A string that will render a table in LaTeX of the equations. + |
+
pysr/sr.py2275 +2276 +2277 +2278 +2279 +2280 +2281 +2282 +2283 +2284 +2285 +2286 +2287 +2288 +2289 +2290 +2291 +2292 +2293 +2294 +2295 +2296 +2297 +2298 +2299 +2300 +2301 +2302 +2303 +2304 +2305 +2306 +2307 +2308 +2309 +2310 +2311 +2312 +2313 +2314 +2315 +2316 +2317 +2318 +2319 +2320 +2321 +2322 +2323 +2324 +2325 +2326 +2327 +2328 +2329 +2330 | |
refresh(checkpoint_file=None)
+
+¶Update self.equations_ with any new options passed.
+For example, updating extra_sympy_mappings
+will require a .refresh() to update the equations.
Parameters:
+| Name | +Type | +Description | +Default | +
|---|---|---|---|
checkpoint_file |
+
+ str
+ |
+
+
+
+ Path to checkpoint hall of fame file to be loaded.
+The default will use the set |
+
+ None
+ |
+
pysr/sr.py