Last active
May 18, 2024 16:07
-
-
Save minesh1291/b1b8f383f431ff51ce760858f9420671 to your computer and use it in GitHub Desktop.
SampleWeights_Regression.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
# Example DataFrame with random target values | |
df = pd.DataFrame({ | |
'label': np.random.normal(size=1000) # 100 random values between 0 and 1 | |
}) | |
# Step 1: Bin the target values to create a frequency distribution | |
df['label_bin'] = pd.cut(df['label'], bins=10) | |
# Step 2: Calculate the frequency of each bin | |
bin_counts = df['label_bin'].value_counts().sort_index() | |
# Step 3: Calculate the weights inversely proportional to the frequency of each bin | |
bin_weights = 1 / bin_counts | |
# Step 4: Assign weights to each sample based on its bin | |
df['weights'] = df['label_bin'].map(bin_weights) | |
# Step 5: Normalize weights to the desired range (optional) | |
min_weight = df['weights'].min() | |
max_weight = df['weights'].max() | |
df['normalized_weights'] = 1 + (df['weights'] - min_weight) * (4 - 1) / (max_weight - min_weight) | |
# Drop the bin column as it's no longer needed | |
df = df.drop(columns=['label_bin']) | |
print(df) | |
plt.hist(df_final_feats['label'], bins=10) | |
plt.plot(df_final_feats['label'], df_final_feats['normalized_weights'], 'o') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment