Spaces:
Sleeping
Sleeping
File size: 7,129 Bytes
f1b19d3 |
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 |
"""
Data Visualizer Tool - Create charts from data
"""
import logging
from typing import Dict, Any
import io
import base64
import sys
import os
# Add parent directory to path for imports
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from utils.helpers import parse_json_safe
logger = logging.getLogger(__name__)
def visualize_data(
data: str,
chart_type: str = "bar",
x_column: str = None,
y_column: str = None,
title: str = "Data Visualization"
) -> Dict[str, Any]:
"""
Create a chart visualization from data.
Args:
data: JSON or CSV string data
chart_type: Type of chart - 'bar', 'line', 'pie', 'scatter'
x_column: X-axis column name
y_column: Y-axis column name
title: Chart title
Returns:
Dictionary with base64 encoded image and metadata
"""
try:
import matplotlib.pyplot as plt
import pandas as pd
import json
# Parse data
try:
# Try JSON first
data_dict = json.loads(data)
df = pd.DataFrame(data_dict)
except json.JSONDecodeError:
# Try CSV
from io import StringIO
df = pd.read_csv(StringIO(data))
if df.empty:
raise ValueError("Data is empty")
# Auto-select columns if not specified
if x_column is None and len(df.columns) > 0:
x_column = df.columns[0]
if y_column is None and len(df.columns) > 1:
y_column = df.columns[1]
elif y_column is None:
y_column = df.columns[0]
# Validate columns exist
if x_column not in df.columns:
raise ValueError(f"Column '{x_column}' not found in data")
if y_column not in df.columns:
raise ValueError(f"Column '{y_column}' not found in data")
# Create figure
plt.figure(figsize=(10, 6))
# Generate chart based on type
if chart_type == "bar":
plt.bar(df[x_column], df[y_column])
plt.xlabel(x_column)
plt.ylabel(y_column)
elif chart_type == "line":
plt.plot(df[x_column], df[y_column], marker='o')
plt.xlabel(x_column)
plt.ylabel(y_column)
plt.grid(True, alpha=0.3)
elif chart_type == "pie":
plt.pie(df[y_column], labels=df[x_column], autopct='%1.1f%%')
elif chart_type == "scatter":
plt.scatter(df[x_column], df[y_column], alpha=0.6)
plt.xlabel(x_column)
plt.ylabel(y_column)
plt.grid(True, alpha=0.3)
else:
raise ValueError(f"Unknown chart type: {chart_type}")
plt.title(title)
plt.tight_layout()
# Convert to base64
buffer = io.BytesIO()
plt.savefig(buffer, format='png', dpi=100, bbox_inches='tight')
buffer.seek(0)
image_base64 = base64.b64encode(buffer.read()).decode('utf-8')
plt.close()
return {
"image_base64": image_base64,
"dimensions": {"width": 1000, "height": 600},
"chart_type": chart_type,
"title": title,
"columns_used": {"x": x_column, "y": y_column}
}
except Exception as e:
logger.error(f"Error creating visualization: {e}")
raise
def create_multi_chart(data: str, chart_configs: list) -> Dict[str, Any]:
"""
Create multiple charts from the same dataset.
Args:
data: JSON or CSV string data
chart_configs: List of chart configuration dictionaries
Returns:
Dictionary with multiple chart images
"""
try:
import matplotlib.pyplot as plt
import pandas as pd
import json
# Parse data once
try:
data_dict = json.loads(data)
df = pd.DataFrame(data_dict)
except json.JSONDecodeError:
from io import StringIO
df = pd.read_csv(StringIO(data))
charts = []
for idx, config in enumerate(chart_configs):
try:
result = visualize_data(
data,
chart_type=config.get("chart_type", "bar"),
x_column=config.get("x_column"),
y_column=config.get("y_column"),
title=config.get("title", f"Chart {idx+1}")
)
charts.append(result)
except Exception as e:
logger.error(f"Error creating chart {idx+1}: {e}")
charts.append({"error": str(e)})
return {
"total_charts": len(charts),
"charts": charts
}
except Exception as e:
logger.error(f"Error creating multi-chart: {e}")
raise
def generate_statistics_chart(data: str) -> Dict[str, Any]:
"""
Generate a statistical summary chart from numeric data.
Args:
data: JSON or CSV string with numeric data
Returns:
Dictionary with statistics chart
"""
try:
import matplotlib.pyplot as plt
import pandas as pd
import json
# Parse data
try:
data_dict = json.loads(data)
df = pd.DataFrame(data_dict)
except json.JSONDecodeError:
from io import StringIO
df = pd.read_csv(StringIO(data))
# Get numeric columns
numeric_cols = df.select_dtypes(include=['number']).columns
if len(numeric_cols) == 0:
raise ValueError("No numeric columns found in data")
# Create statistics summary
fig, axes = plt.subplots(1, 2, figsize=(14, 6))
# Box plot
df[numeric_cols].boxplot(ax=axes[0])
axes[0].set_title("Distribution (Box Plot)")
axes[0].set_ylabel("Values")
# Histogram
df[numeric_cols].hist(ax=axes[1], bins=20, alpha=0.7)
axes[1].set_title("Distribution (Histogram)")
plt.tight_layout()
# Convert to base64
buffer = io.BytesIO()
plt.savefig(buffer, format='png', dpi=100, bbox_inches='tight')
buffer.seek(0)
image_base64 = base64.b64encode(buffer.read()).decode('utf-8')
plt.close()
# Calculate statistics
stats = df[numeric_cols].describe().to_dict()
return {
"image_base64": image_base64,
"statistics": stats,
"numeric_columns": list(numeric_cols)
}
except Exception as e:
logger.error(f"Error generating statistics chart: {e}")
raise
|