IoT Sensor Correlations

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
from matplotlib.colors import LinearSegmentedColormap

np.random.seed(42)

# Sensors
sensors = ['Temp_In', 'Temp_Out', 'Humidity', 'CO2', 'Light', 
           'Motion', 'Door', 'Window', 'HVAC', 'Power']
n = len(sensors)

# Create correlation structure
corr = np.eye(n)
# Temperature correlations
corr[0, 1] = corr[1, 0] = 0.7
corr[0, 8] = corr[8, 0] = -0.6  # HVAC vs temp
corr[2, 0] = corr[0, 2] = -0.4  # Humidity vs temp
# Activity correlations
corr[5, 6] = corr[6, 5] = 0.5  # Motion/door
corr[5, 4] = corr[4, 5] = 0.6  # Motion/light
corr[8, 9] = corr[9, 8] = 0.8  # HVAC/power

# Fill rest with weak correlations
for i in range(n):
    for j in range(i+1, n):
        if corr[i, j] == 0:
            corr[i, j] = corr[j, i] = np.random.uniform(-0.2, 0.2)

df = pd.DataFrame(corr, index=sensors, columns=sensors)

# NEON diverging
neon_div = LinearSegmentedColormap.from_list('neon_div', ['#27D3F5', '#0a0a0f', '#F527B0'])

g = sns.clustermap(df, cmap=neon_div, center=0, vmin=-1, vmax=1,
                   method='average', linewidths=0.5, linecolor='#1a1a2e',
                   figsize=(8, 7), dendrogram_ratio=(0.12, 0.12),
                   annot=True, fmt='.2f', annot_kws={'size': 8, 'color': 'white'},
                   cbar_pos=(0.01, 0.08, 0.008, 0.12),
                   tree_kws={'linewidths': 1.5, 'colors': '#27D3F5'})

g.fig.patch.set_facecolor('#0a0a0f')
g.ax_heatmap.set_facecolor('#0a0a0f')
g.ax_heatmap.tick_params(colors='white', labelsize=9)

for ax in [g.ax_row_dendrogram, g.ax_col_dendrogram]:
    ax.set_facecolor('#0a0a0f')

g.fig.suptitle('Smart Home Sensor Correlations', color='white', fontsize=14, fontweight='bold', y=1.02)


plt.show()