# DecimalScaling Class for Normalizing Features Using Decimal Scaling Technique
# **Importing and Using the DecimalScaling Class in a Python Program**
#
# import pandas as pd
#
# from geoanalytics.normalization import DecimalScaling
#
# df = pd.read_csv("input.csv")
#
# scaler = DecimalScaling(df)
#
# normalized_df = scaler.run()
#
# scaler.getRuntime()
#
# scaler.getMemoryUSS()
#
# scaler.getMemoryRSS()
#
# scaler.save("DecimalScaling.csv")
#
__copyright__ = """
Copyright (C) 2022 Rage Uday Kiran
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
"""
import time
import psutil
from tqdm import tqdm
import numpy as np
import pandas as pd
[docs]
class DecimalScaling:
"""
**About this algorithm**
:**Description**:
DecimalScaling is a normalization technique that transforms features by dividing them
by powers of 10 based on the maximum absolute value. This class normalizes all feature
columns (excluding coordinates) to scale them within a decimal range, while also tracking
memory usage and execution time.
:**Parameters**:
- `dataframe` (*pd.DataFrame*): Input DataFrame containing 'x', 'y', and feature columns.
:**Attributes**:
- **df** (*pd.DataFrame*) -- Original DataFrame with renamed columns.
- **normalizedDF** (*pd.DataFrame*) -- DataFrame after normalization.
- **startTime, endTime** (*float*) -- Timestamps for runtime tracking.
- **memoryUSS, memoryRSS** (*float*) -- Memory usage (USS and RSS) in kilobytes.
**Execution methods**
**Calling from a Python program**
.. code-block:: python
import pandas as pd
from geoanalytics.normalization import DecimalScaling
df = pd.read_csv("input.csv")
scaler = DecimalScaling(df)
normalized_df = scaler.run()
scaler.getRuntime()
scaler.getMemoryUSS()
scaler.getMemoryRSS()
scaler.save("DecimalScaling.csv")
**Credits**
This implementation was created by Raashika and revised by M. Charan Teja under the guidance of Professor Rage Uday Kiran.
"""
def __init__(self, dataframe):
"""
Initializes the DecimalScaling object with a copy of the dataframe.
"""
self.df = dataframe.copy()
self.df.columns = ['x', 'y'] + list(self.df.columns[2:])
self.normalizedDF = None
self.startTime = None
self.endTime = None
self.memoryUSS = None
self.memoryRSS = None
[docs]
def getRuntime(self):
"""
Prints the total runtime of the clustering algorithm.
"""
print("Total Execution time of proposed Algorithm:", self.endTime - self.startTime, "seconds")
[docs]
def getMemoryUSS(self):
"""
Prints the memory usage (USS) of the process in kilobytes.
"""
print("Memory (USS) of proposed Algorithm in KB:", self.memoryUSS)
[docs]
def run(self):
"""
Applies Decimal Scaling normalization to the input features.
Returns:
pd.DataFrame: Normalized DataFrame with 'x', 'y', and scaled features.
"""
self.startTime = time.time()
xy = self.df[['x', 'y']].reset_index(drop=True)
data = self.df.drop(['x', 'y'], axis=1).reset_index(drop=True)
maxAbs = data.abs().max().max()
numDigits = int(np.ceil(np.log10(maxAbs)))
divisor = 10 ** numDigits
normalizedData = data / divisor
self.normalizedDF = pd.concat([xy, normalizedData], axis=1)
self.endTime = time.time()
process = psutil.Process()
self.memoryUSS = process.memory_full_info().uss / 1024
self.memoryRSS = process.memory_full_info().rss / 1024
return self.normalizedDF
[docs]
def save(self, outputFile='DecimalScaling.csv'):
"""
Saves the Normalized DataFrame to a CSV file.
"""
if self.normalizedDF is not None:
try:
self.normalizedDF.to_csv(outputFile, index=False)
print(f"Normalized data saved to: {outputFile}")
except Exception as e:
print(f"Failed to save labels: {e}")
else:
print("No Normalized data to save. Execute run() method first")