data-visualization

Data Visualization for Construction

Overview

Based on DDC methodology (Chapter 4.1), this skill provides comprehensive data visualization techniques for construction analytics. Visual insights drive better decisions - from cost breakdowns to schedule analysis.

Book Reference: "Аналитика данных и принятие решений" / "Data Analytics and Decision Making"

"Визуализация данных превращает сложные наборы данных в понятные графики, которые могут использоваться для принятия решений на всех уровнях проекта."

— DDC Book, Chapter 4.1

Quick Start

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load construction data
df = pd.read_excel("project_data.xlsx")

# Quick bar chart - volumes by category
fig, ax = plt.subplots(figsize=(10, 6))
df.groupby('Category')['Volume_m3'].sum().plot(kind='bar', ax=ax)
ax.set_title('Volume by Category')
ax.set_ylabel('Volume (m³)')
plt.tight_layout()
plt.savefig('volume_by_category.png', dpi=150)
plt.show()

Matplotlib Fundamentals

Basic Charts for Construction

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

def create_cost_breakdown_pie(df, cost_col='Cost', category_col='Category'):
    """Create pie chart for cost breakdown"""
    costs = df.groupby(category_col)[cost_col].sum()

    fig, ax = plt.subplots(figsize=(10, 8))

    # Create pie with percentage labels
    wedges, texts, autotexts = ax.pie(
        costs.values,
        labels=costs.index,
        autopct='%1.1f%%',
        startangle=90,
        colors=plt.cm.Set3.colors
    )

    ax.set_title('Cost Breakdown by Category', fontsize=14, fontweight='bold')

    # Add total in center
    ax.text(0, 0, f'Total:\n${costs.sum():,.0f}',
            ha='center', va='center', fontsize=12)

    plt.tight_layout()
    return fig

def create_volume_bar_chart(df, volume_col='Volume_m3', category_col='Category'):
    """Create horizontal bar chart for volumes"""
    volumes = df.groupby(category_col)[volume_col].sum().sort_values()

    fig, ax = plt.subplots(figsize=(10, 6))

    bars = ax.barh(volumes.index, volumes.values, color='steelblue')

    # Add value labels
    for bar, value in zip(bars, volumes.values):
        ax.text(value + volumes.max() * 0.01, bar.get_y() + bar.get_height()/2,
                f'{value:,.0f} m³', va='center', fontsize=10)

    ax.set_xlabel('Volume (m³)')
    ax.set_title('Material Volumes by Category', fontsize=14, fontweight='bold')
    ax.set_xlim(0, volumes.max() * 1.15)

    plt.tight_layout()
    return fig

def create_level_comparison(df, value_col='Volume_m3', level_col='Level'):
    """Create grouped bar chart comparing levels"""
    pivot = df.pivot_table(
        values=value_col,
        index=level_col,
        columns='Category',
        aggfunc='sum',
        fill_value=0
    )

    fig, ax = plt.subplots(figsize=(12, 6))
    pivot.plot(kind='bar', ax=ax, width=0.8)

    ax.set_xlabel('Building Level')
    ax.set_ylabel('Volume (m³)')
    ax.set_title('Volume Distribution by Level and Category', fontsize=14, fontweight='bold')
    ax.legend(title='Category', bbox_to_anchor=(1.02, 1), loc='upper left')

    plt.xticks(rotation=45)
    plt.tight_layout()
    return fig

Time Series Visualization

def create_progress_chart(df, date_col='Date', value_col='Cumulative_Progress'):
    """Create S-curve progress chart"""
    df = df.sort_values(date_col)

    fig, ax = plt.subplots(figsize=(12, 6))

    # Actual progress
    ax.plot(df[date_col], df[value_col],
            'b-', linewidth=2, label='Actual Progress')

    # Planned progress (if available)
    if 'Planned_Progress' in df.columns:
        ax.plot(df[date_col], df['Planned_Progress'],
                'g--', linewidth=2, label='Planned Progress')

    ax.fill_between(df[date_col], 0, df[value_col], alpha=0.3)

    ax.set_xlabel('Date')
    ax.set_ylabel('Progress (%)')
    ax.set_title('Project S-Curve', fontsize=14, fontweight='bold')
    ax.legend()
    ax.grid(True, alpha=0.3)

    # Format dates
    fig.autofmt_xdate()

    plt.tight_layout()
    return fig

def create_gantt_chart(df, start_col='Start', end_col='End', task_col='Task'):
    """Create simple Gantt chart"""
    df = df.sort_values(start_col)

    fig, ax = plt.subplots(figsize=(14, len(df) * 0.5 + 2))

    # Plot each task as horizontal bar
    for i, (_, row) in enumerate(df.iterrows()):
        start = pd.to_datetime(row[start_col])
        end = pd.to_datetime(row[end_col])
        duration = (end - start).days

        ax.barh(i, duration, left=start, height=0.6,
                align='center', color='steelblue', alpha=0.8)

    ax.set_yticks(range(len(df)))
    ax.set_yticklabels(df[task_col])
    ax.set_xlabel('Date')
    ax.set_title('Project Schedule - Gantt Chart', fontsize=14, fontweight='bold')
    ax.grid(axis='x', alpha=0.3)

    fig.autofmt_xdate()
    plt.tight_layout()
    return fig

Seaborn for Statistical Visualization

Distribution Analysis

import seaborn as sns

def create_distribution_analysis(df, value_col='Volume_m3', category_col='Category'):
    """Create distribution plots for construction data"""
    fig, axes = plt.subplots(2, 2, figsize=(14, 10))

    # 1. Histogram with KDE
    sns.histplot(data=df, x=value_col, kde=True, ax=axes[0, 0])
    axes[0, 0].set_title('Volume Distribution')

    # 2. Box plot by category
    sns.boxplot(data=df, x=category_col, y=value_col, ax=axes[0, 1])
    axes[0, 1].set_xticklabels(axes[0, 1].get_xticklabels(), rotation=45)
    axes[0, 1].set_title('Volume by Category')

    # 3. Violin plot
    sns.violinplot(data=df, x=category_col, y=value_col, ax=axes[1, 0])
    axes[1, 0].set_xticklabels(axes[1, 0].get_xticklabels(), rotation=45)
    axes[1, 0].set_title('Volume Distribution by Category')

    # 4. Strip plot with jitter
    sns.stripplot(data=df, x=category_col, y=value_col,
                  ax=axes[1, 1], alpha=0.5, jitter=True)
    axes[1, 1].set_xticklabels(axes[1, 1].get_xticklabels(), rotation=45)
    axes[1, 1].set_title('Individual Elements')

    plt.tight_layout()
    return fig

def create_correlation_heatmap(df, numeric_cols=None):
    """Create correlation heatmap for numeric columns"""
    if numeric_cols is None:
        numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()

    corr_matrix = df[numeric_cols].corr()

    fig, ax = plt.subplots(figsize=(10, 8))

    sns.heatmap(corr_matrix,
                annot=True,
                cmap='RdYlBu_r',
                center=0,
                fmt='.2f',
                square=True,
                ax=ax)

    ax.set_title('Correlation Matrix', fontsize=14, fontweight='bold')

    plt.tight_layout()
    return fig

Category Analysis

def create_category_summary(df, category_col='Category',
                            value_col='Volume_m3', cost_col='Cost'):
    """Create comprehensive category summary visualization"""
    fig, axes = plt.subplots(2, 2, figsize=(14, 10))

    # 1. Count by category
    category_counts = df[category_col].value_counts()
    sns.barplot(x=category_counts.index, y=category_counts.values, ax=axes[0, 0])
    axes[0, 0].set_title('Element Count by Category')
    axes[0, 0].set_xticklabels(axes[0, 0].get_xticklabels(), rotation=45)

    # 2. Total volume by category
    volumes = df.groupby(category_col)[value_col].sum().sort_values(ascending=False)
    sns.barplot(x=volumes.index, y=volumes.values, ax=axes[0, 1])
    axes[0, 1].set_title('Total Volume by Category')
    axes[0, 1].set_xticklabels(axes[0, 1].get_xticklabels(), rotation=45)

    # 3. Average cost by category
    if cost_col in df.columns:
        avg_cost = df.groupby(category_col)[cost_col].mean().sort_values(ascending=False)
        sns.barplot(x=avg_cost.index, y=avg_cost.values, ax=axes[1, 0])
        axes[1, 0].set_title('Average Cost by Category')
        axes[1, 0].set_xticklabels(axes[1, 0].get_xticklabels