FIX: Geometric distribution declaration & test

change all "lambda" to "lambda_" in distribution.cpp for only geometric distribution
adjust geometric distribution test to use "lambda_" keyword

Description

When running GaussianNB class in the PyDP_Naive_Bayes.ipynb file, the following error appears:

TypeError: __init__(): incompatible constructor arguments. The following argument types are supported:
    1. pydp.GeometricDistribution(lambda: float)
Invoked with: kwargs: lambda_=0.020202707317519466

This is because, the GeometricDistribution supposed to take in lambda, and not lambda_. However, the word lambda in Python refers to the lambda function; therefore, GeometricDistribution has been adjusted to accept lambda_ instead of lambda (see src/bindings/PyDP/algorithms/distributions.cpp). Test file has also been adjusted (see /tests/algorithms/test_distributions.py)

Affected Dependencies

GeometricDistribution has been adjusted to accept lambda_ instead of lambda.

How has this been tested?

Has been tested in the notebook PyDP_Naive_Bayes.ipynb

Checklist

[x] I have followed the Contribution Guidelines and Code of Conduct
[x] I have commented my code following the OpenMined Styleguide
[x] I have labeled this PR with the relevant Type labels
[x] My changes are covered by tests

OpenMined / PyDP