|
| 1 | +import numpy as np |
1 | 2 | import matplotlib.pyplot as plt |
2 | 3 | import json |
3 | 4 |
|
4 | 5 | def analyze_data(data): |
5 | 6 | numbers = data.get("numbers", []) |
6 | | - |
7 | 7 | if not numbers: |
8 | | - return {"error": "No numbers provided for analysis"} |
| 8 | + return {"error": "No numbers provided"} |
9 | 9 |
|
10 | | - average = sum(numbers) / len(numbers) |
11 | | - |
12 | | - result = { |
13 | | - "average": average, |
14 | | - "category": "High" if average > 50 else "Low", |
15 | | - "input_size": len(numbers), |
| 10 | + arr = np.array(numbers) |
| 11 | + mean = arr.mean() |
| 12 | + median = np.median(arr) |
| 13 | + std_dev = arr.std() |
| 14 | + # Possibly detect outliers |
| 15 | + outliers = arr[np.abs(arr - mean) > 2 * std_dev] |
| 16 | + |
| 17 | + return { |
| 18 | + "mean": mean, |
| 19 | + "median": median, |
| 20 | + "std_dev": std_dev, |
| 21 | + "outliers": outliers.tolist() |
16 | 22 | } |
17 | | - return result |
18 | 23 |
|
19 | 24 | def visualize_analysis(result, filename="./output/analysis_visualization.png"): |
20 | | - # Extract values |
21 | | - average = result["average"] |
22 | | - category = result["category"] |
23 | | - input_size = result["input_size"] |
24 | | - |
25 | | - # Visualization |
26 | | - plt.figure(figsize=(8, 5)) |
27 | | - |
28 | | - # Bar chart for numeric values |
29 | | - metrics = ["Average", "Input Size"] |
30 | | - values = [average, input_size] |
31 | | - colors = ["blue", "green"] |
32 | | - |
33 | | - plt.bar(metrics, values, color=colors, alpha=0.7) |
34 | | - |
35 | | - # Add titles and labels |
36 | | - plt.title(f"Data Analysis Visualization(METACALL)\nCategory: {category}", fontsize=14, pad=15) |
37 | | - plt.xlabel("Metrics", fontsize=12) |
38 | | - plt.ylabel("Values", fontsize=12) |
39 | | - |
40 | | - # Add value labels on top of bars |
41 | | - for i, value in enumerate(values): |
42 | | - plt.text(i, value + 1, f"{value:.2f}", ha="center", va="bottom", fontsize=10) |
43 | | - |
44 | | - # Grid for better readability |
45 | | - plt.grid(axis="y", linestyle="--", alpha=0.7) |
46 | | - |
47 | | - # Save the plot to a file |
| 25 | + mean = result["mean"] |
| 26 | + std_dev = result["std_dev"] |
| 27 | + outliers = result["outliers"] |
| 28 | + |
| 29 | + fig, ax = plt.subplots(2, 1, figsize=(8, 8)) |
| 30 | + |
| 31 | + # Top subplot: bar chart |
| 32 | + metrics = ["Mean", "Standard Deviation"] |
| 33 | + values = [mean, std_dev] |
| 34 | + ax[0].bar(metrics, values, color=["blue", "red"]) |
| 35 | + ax[0].set_title("Basic Statistics", fontsize=14) |
| 36 | + |
| 37 | + # Bottom subplot: outliers |
| 38 | + ax[1].bar(range(len(outliers)), outliers, color="orange") |
| 39 | + ax[1].set_title("Detected Outliers", fontsize=14) |
| 40 | + |
48 | 41 | plt.tight_layout() |
49 | 42 | plt.savefig(filename, dpi=300) |
50 | 43 | plt.close() |
51 | | - print(f"Visualization saved as {filename}") |
| 44 | + print(f"Visualization saved as {filename}") |
| 45 | + |
52 | 46 |
|
53 | 47 |
|
54 | 48 | def process_message(message): |
|
0 commit comments