my snippets

clean.py

# remove outliner
upper = df.quantile(0.99)

cols = set(list(df)) - {"ts", "tss"}
df_clean = df
for col in cols:
    df_clean = df_clean[(df_clean[col] < upper[col])]

multi scatter plot.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# Create a sample data set with three variables
data = pd.DataFrame(np.random.randn(1000, 4), columns=['Variable 1', 'Variable 2', 'Variable 3', 'Variables 4'])
target_variable = np.random.randn(1000)

# Create a multi-scatter plot for all variables against the target variable
fig, axs = plt.subplots(nrows=3, ncols=2, figsize=(10, 12))
axs = axs.flatten()
for i, variable in enumerate(data.columns):
    axs[i].scatter(data[variable], target_variable, alpha=0.2)
    axs[i].set_xlabel(variable)
    axs[i].set_ylabel('Target Variable')
plt.tight_layout()
plt.show()