Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
基于多维度数据进行分级评估与趋势预测,通过设定差异化增长率计算预测值,并生成对比可视化图表,适用于绩效评估、目标设定等场景。
Step1 加载数据并配置环境,设置中文字体以确保可视化图表正常显示。
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')
# 设置中文字体,优先使用 WenQuanYi Zen Hei,备选 SimHei 和 DejaVu Sans
plt.rcParams['font.sans-serif'] = ['WenQuanYi Zen Hei', 'SimHei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False
# 加载数据文件
file_path = 'your_data.xlsx'
df = pd.read_excel(file_path)
print(f"数据形状: {df.shape}")
df.head()
Step2 基于数据表现划分等级并设定差异化增长率,计算预测结果。
# 定义通用列名
group_col = '分组列名' # 示例:'部门'、'产品线'
target_col = '目标数值列名' # 示例:'销售额'、'产量'
# 计算各维度的总值并排序
performance_data = df.groupby(group_col, as_index=False)[target_col].sum().sort_values(by=target_col, ascending=False)
# 划分等级(前30%为高,后30%为低,其余为中等)
n = len(performance_data)
high_perf_threshold = int(0.3 * n)
low_perf_threshold = int(0.7 * n)
performance_data['等级'] = '中等'
performance_data.loc[:high_perf_threshold-1, '等级'] = '高'
performance_data.loc[low_perf_threshold:, '等级'] = '低'
# 设定预测增长率映射字典
growth_rate_map = {
'高': 0.10, # 10% 增长率
'中等': 0.08, # 8% 增长率
'低': 0.15 # 15% 增长率
}
performance_data['预测增长率'] = performance_data['等级'].map(growth_rate_map)
npx skills add OpenSenseNova/SenseNova-Skills --skill trend-analysisHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Clear and well structured, with only minor parts that might need a second read.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Mostly actionable with clear steps; only a few small gaps remain.