python数据挖掘使用Evidently创建机器学习模型仪表板

$ pip install evidently

$ jupyter nbextension install --sys-prefix --symlink --overwrite --py evidently

jupyter nbextension enable evidently --py --sys-prefix

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from evidently.dashboard import Dashboard
from evidently.tabs import RegressionPerformanceTab
from evidently.model_profile import Profile
from evidently.profile_sections import RegressionPerformanceProfileSection

raw_data = pd.read_csv('/content/day.csv', header = 0, sep = ',', parse_dates=['dteday'])
ref_data = raw_data[:120]
prod_data = raw_data[120:150]
ref_data.head()

target = 'cnt'
datetime = 'dteday'
numerical_features = ['mnth', 'temp', 'atemp', 'hum', 'windspeed']
categorical_features = ['season', 'holiday', 'weekday', 'workingday', 'weathersit',]
features = numerical_features + categorical_features
model = RandomForestRegressor(random_state = 0)
model.fit(ref_data[features], ref_data[target])
ref_data['prediction']  = model.predict(ref_data[features])
prod_data['prediction'] = model.predict(prod_data[features])

column_mapping = {}
column_mapping['target'] = target
column_mapping['prediction'] = 'prediction'
column_mapping['datetime'] = datetime
column_mapping['numerical_features'] = numerical_features
column_mapping['categorical_features'] = categorical_features
dashboard = Dashboard(tabs=[RegressionPerformanceTab])
dashboard .calculate(ref_data, prod_data, column_mapping=column_mapping)
dashboard.save('bike_sharing_demand_model_perfomance.html')