How to create SMILE DataSet from a pandas dataframe?

[BayesFusionUser123]

I want to use this method
read_pandas_dataframe(self: pysmile.learning.DataSet, *args, **kwargs) -> None
to create DataSet object directly from a pandas dataframe.

Could you please tell me how can I fix this issue? Thanks.
The sample code is below:

Code: Select all

# %%
import pandas as pd
import pysmile
import pysmile_license
import numpy as np
import os
import scipy
import math
from functools import partial

# %%
def simulate_bayesian_network():
    # Set random seed for reproducibility
    np.random.seed(1)

    N = 50000

    # Step 1: B ~ Bernoulli(0.5)
    B = np.random.binomial(1, 0.5, size=(N,))

    # Step 2: A depends on B
    A = np.zeros(N, dtype=int)
    A[B == 1] = np.random.binomial(1, 0.9, size=(np.sum(B == 1),))
    A[B == 0] = np.random.binomial(1, 0.1, size=(np.sum(B == 0),))

    # Step 3: T depends on A and B
    T = np.zeros(N, dtype=int)
    T[(A == 1) & (B == 1)] = np.random.binomial(1, 0.9, size=np.sum((A == 1) & (B == 1)))
    T[(A == 1) & (B == 0)] = np.random.binomial(1, 0.1, size=np.sum((A == 1) & (B == 0)))
    T[(A == 0) & (B == 1)] = np.random.binomial(1, 0.1, size=np.sum((A == 0) & (B == 1)))
    T[(A == 0) & (B == 0)] = np.random.binomial(1, 0.1, size=np.sum((A == 0) & (B == 0)))
    
    data = {}
    data['A'] = A
    data['B'] = B
    data['T'] = T

    return pd.DataFrame(data)

# Simulate and preview the dataset
data = simulate_bayesian_network()
print(data.head())
print(type(data))

# %%
def assign_category_name_to_discrete_variables(df, variable_list):
    # the variables that are categorical, but represented by numbers like 0, 1, 2
    # convert it to form var_0, var_1, var_2
    
    def process_categorical_name(x, prefix):
        x = str(x)
        return f"{prefix}___{x}"
    
    for var in variable_list:
        my_func_for_x = partial(process_categorical_name, prefix=var)
        df[var] = df[var].apply(my_func_for_x)
    #endfor
    
    return df

# %%
assign_category_name_to_discrete_variables(data, ["A", "B", "T"])

# %%
print(type(data))

# %%
data.info()

# %%
# read_pandas_dataframe(self: pysmile.learning.DataSet, *args, **kwargs) -> None
# Reads data from a pandas DataFrame

data = data.astype("string")
for col in data.select_dtypes(include=['string', 'object']).columns:
    data[col] = data[col].astype('category')
#endfor
data = data.reset_index(drop=True)

ds_1 = pysmile.learning.DataSet()
ds_1.read_pandas_dataframe(data)

The error message is like:

Code: Select all

# Traceback (most recent call last):
#   File "/create_SMILE_DataSet_from_pandas_dataframe.py", line 92, in <module>
#     ds_1.read_pandas_dataframe(data)
#   File "/users/anaconda3/envs/smile/lib/python3.11/site-packages/pandas/core/generic.py", line 6318, in __getattr__
#     return object.__getattribute__(self, name)
#            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# AttributeError: 'DataFrame' object has no attribute 'dtype'. Did you mean: 'dtypes'?

[piotr [BayesFusion]]

Thank you for reporting this issue.

The problem was caused by a naming conflict: "T" is a built-in pandas DataFrame property that returns the transpose of the DataFrame.

Workaround for now: rename any column called T to something else (e.g. C). Other pandas attribute names to avoid as column names include: at, iat, loc, iloc, shape, columns, index, dtypes, values, axes, ndim, size, empty.

In the next PySMILE release we will fix the root cause - after that, no renaming will be necessary.