From 653cb680d6cedf247f38ebb743b9fae92c5dccd3 Mon Sep 17 00:00:00 2001
From: Brandon Rodriguez <brodriguez8774@gmail.com>
Date: Mon, 21 May 2018 12:19:06 -0400
Subject: [PATCH] Set up base class structure
---
main.py | 28 +++++++++++++++++
neural_net.py | 71 ++++++++++++++++++++++++++++++++++++++++++++
resources/logging.py | 2 +-
3 files changed, 100 insertions(+), 1 deletion(-)
create mode 100644 neural_net.py
diff --git a/main.py b/main.py
index e69de29..927ef8a 100644
--- a/main.py
+++ b/main.py
@@ -0,0 +1,28 @@
+"""
+Back-propagation Neural Net.
+"""
+
+# System Imports.
+import numpy, pandas
+
+# User Class Imports.
+from resources import logging
+import neural_net
+
+
+# Initialize logging.
+logger = logging.get_logger(__name__)
+
+
+# Load in CSV.
+housing_data = pandas.read_csv('./Documents/other_housing.csv')
+
+# Initially only work with first 10, for testing purposes.
+housing_data = housing_data[0:10]
+
+# Normalize data.
+normalizer = neural_net.Normalizer()
+normalized_data = normalizer.normalize_data(housing_data)
+
+# Start neural net.
+backprop = neural_net.BackPropNet(normalized_data)
diff --git a/neural_net.py b/neural_net.py
new file mode 100644
index 0000000..3ad7ce1
--- /dev/null
+++ b/neural_net.py
@@ -0,0 +1,71 @@
+"""
+Neural Net logic.
+"""
+
+# System Imports.
+import numpy, pandas
+
+# User Class Imports.
+from resources import logging
+
+
+# Initialize logging.
+logger = logging.get_logger(__name__)
+
+
+class Normalizer():
+ """
+ Handles data normalization.
+ """
+ def normalize_data(self, data):
+ """
+ Normalizes and returns provided dataset.
+ :param data: A pandas array of housing data to normalize.
+ :return: The normalized array of housing data.
+ """
+ # Print out data.
+ # logger.info(data)
+ # logger.info(data.columns.values)
+
+ # Address individual columns.
+
+ return data
+
+class BackPropNet():
+ """
+ Neural Net implementing back propagation.
+ """
+ def __init__(self, data):
+ self.weights = self._initialize_weights(data)
+
+ def _initialize_weights(self, data):
+ """
+ Initialize weights based of number of passed columns in data.
+ Values are initialized to random decimals near 0, using a normal distribution.
+ :param data: Data to create weights for.
+ :return: Vector of column weights.
+ """
+ weights = []
+ for column in data.columns:
+ weights.append(numpy.random.randn() * 0.001)
+
+ # logger.info(weights)
+ return weights
+
+ def predict(self):
+ pass
+
+ def train(self):
+ pass
+
+ def _train_step(self):
+ pass
+
+ def _calculate_error(self):
+ pass
+
+
+class ResultTracker():
+ """
+ Tracks statistics and progress of main Neural Net class.
+ """
diff --git a/resources/logging.py b/resources/logging.py
index c247173..f4cf655 100644
--- a/resources/logging.py
+++ b/resources/logging.py
@@ -22,7 +22,7 @@ def get_logger(caller):
project_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
log_dir = os.path.join(project_dir, 'resources/logs')
if not os.path.exists(log_dir):
- print('Error initializing logging.')
+ os.makedirs(log_dir)
# Dictionary style logging options.
--
GitLab