init weights and biases, and getting through epochs

.gitignore

@@ -24,4 +24,165 @@ go.work
 .vscode
 .idea
 
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
 *.swp

nn/nn.py

@@ -24,8 +24,6 @@ class NN:
         self.target = target
         self.data = data
 
-        self.input_size = len(features)
-
         self.wh: np.array = None
         self.wo: np.array = None
         self.bh: np.array = None
@@ -39,8 +37,12 @@ class NN:
     def set_df(self, df: pd.DataFrame) -> None:
         assert isinstance(df, pd.DataFrame)
         self.df = df
-        self.X = df[self.features]
-        self.y = df[self.target]
+        # we can only deal with numbers from here on out
+        y = df[self.target]
+        x = df[self.features]
+        self.y = pd.get_dummies(y, columns=self.target)
+        self.X = pd.get_dummies(x, columns=self.features)
+        self.input_size = len(self.X.columns)
 
     def set_func(self, f: Callable) -> None:
         assert isinstance(f, Callable)

nn/train.py

@@ -1,15 +1,16 @@
 from sklearn.model_selection import train_test_split
+from typing import Callable
 from nn.nn import NN
 import pandas as pd
 import numpy as np
 
 
 def init_weights_biases(nn: NN) -> None:
-    np.random.seed(88)
-    bh = np.zeros((1, 1))
+    bh = np.zeros((1, nn.hidden_size))
     bo = np.zeros((1, 1))
-    wh = np.random.randn(1, nn.input_size) * np.sqrt(2 / nn.input_size)
-    wo = np.random.randn(1, nn.hidden_size) * np.sqrt(2 / nn.hidden_size)
+    wh = np.random.randn(nn.input_size, nn.hidden_size) * \
+        np.sqrt(2 / nn.input_size)
+    wo = np.random.randn(nn.hidden_size, 1) * np.sqrt(2 / nn.hidden_size)
     nn.set_bh(bh)
     nn.set_bo(bo)
     nn.set_wh(wh)
@@ -22,7 +23,33 @@ def train(nn: NN) -> dict:
         nn.X,
         nn.y,
         test_size=nn.test_size,
-        random_state=88,
     )
 
-    return {"status": "you made it!"}
+    for _ in range(nn.epochs):
+        # compute hidden output
+        hidden_output = compute_node(
+            data=X_train.to_numpy(),
+            weights=nn.wh,
+            biases=nn.bh,
+            func=nn.func,
+        )
+
+        # compute output layer
+        y_hat = compute_node(
+            data=hidden_output,
+            weights=nn.wo,
+            biases=nn.bo,
+            func=nn.func,
+        )
+
+        mse = mean_squared_error(y_train, y_hat)
+
+    return {"mse": mse}
+
+
+def compute_node(data: np.array, weights: np.array, biases: np.array, func: Callable) -> np.array:
+    return func(np.dot(data, weights) + biases)
+
+
+def mean_squared_error(y: np.array, y_hat: np.array) -> np.array:
+    return np.mean((y - y_hat) ** 2)