File size: 1,597 Bytes
b22d66b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
class VisualizationSelector:
def select_visualizations(self, data):
visualizations = []
# Histogram for numerical columns
numeric_columns = data.select_dtypes(include=[np.number]).columns
for column in numeric_columns:
fig, ax = plt.subplots()
sns.histplot(data[column], kde=True, ax=ax)
ax.set_title(f'Distribution of {column}')
visualizations.append(fig)
# Correlation heatmap
if len(numeric_columns) > 1:
fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(data[numeric_columns].corr(), annot=True, cmap='coolwarm', ax=ax)
ax.set_title('Correlation Heatmap')
visualizations.append(fig)
# Scatter plot matrix
if len(numeric_columns) > 1:
fig = sns.pairplot(data[numeric_columns])
fig.fig.suptitle('Scatter Plot Matrix', y=1.02)
visualizations.append(fig)
# Box plots for categorical vs numerical
categorical_columns = data.select_dtypes(include=['object']).columns
for cat_col in categorical_columns:
for num_col in numeric_columns:
fig, ax = plt.subplots()
sns.boxplot(x=cat_col, y=num_col, data=data, ax=ax)
ax.set_title(f'{cat_col} vs {num_col}')
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')
visualizations.append(fig)
return visualizations |