Platform For AI:Analyse des erreurs

!pip install raiwidgets==0.34.1

# Import dependencies for Responsible AI

import zipfile
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer

import pandas as pd
from lightgbm import LGBMClassifier
from raiutils.dataset import fetch_dataset
import sklearn
from packaging import version
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer

# Specify the name of the dataset file.
outdirname = 'responsibleai.12.28.21'
zipfilename = outdirname + '.zip'

# Download and extract the dataset.
fetch_dataset('https://publictestdatasets.blob.core.windows.net/data/' + zipfilename, zipfilename)
with zipfile.ZipFile(zipfilename, 'r') as unzip:
    unzip.extractall('.')

# Load the training and test data.
train_data = pd.read_csv('adult-train.csv', skipinitialspace=True)
test_data = pd.read_csv('adult-test.csv', skipinitialspace=True)

# Define the columns for the features and the target variable.
target_feature = 'income'
categorical_features = ['workclass', 'education', 'marital-status',
                        'occupation', 'relationship', 'race', 'gender', 'native-country']

# Define a function to split the features and the target variable.
def split_label(dataset, target_feature):
    X = dataset.drop([target_feature], axis=1)
    y = dataset[[target_feature]]
    return X, y

# Split the features and the target variable.
X_train_original, y_train = split_label(train_data, target_feature)
X_test_original, y_test = split_label(test_data, target_feature)

# Convert to the NumPy format.
y_train = y_train[target_feature].to_numpy()
y_test = y_test[target_feature].to_numpy()

# Define a test sample.
test_data_sample = test_data.sample(n=500, random_state=5)

import pandas as pd

# Load your own dataset in CSV format.
# Use pandas to read the CSV file.
try:
    data = pd.read_csv(filename)
except:
    pass

# Define the ohe_params parameter based on the scikit-learn version.
if version.parse(sklearn.__version__) < version.parse('1.2'):
    ohe_params = {"sparse": False}
else:
    ohe_params = {"sparse_output": False}

# Define the classification pipeline for feature transformation. The input parameter X represents the training data.
def create_classification_pipeline(X):
    pipe_cfg = {
        'num_cols': X.dtypes[X.dtypes == 'int64'].index.values.tolist(),
        'cat_cols': X.dtypes[X.dtypes == 'object'].index.values.tolist(),
    }
    num_pipe = Pipeline([
        ('num_imputer', SimpleImputer(strategy='median')),
        ('num_scaler', StandardScaler())
    ])
    cat_pipe = Pipeline([
        ('cat_imputer', SimpleImputer(strategy='constant', fill_value='?')),
        ('cat_encoder', OneHotEncoder(handle_unknown='ignore', **ohe_params))
    ])
    feat_pipe = ColumnTransformer([
        ('num_pipe', num_pipe, pipe_cfg['num_cols']),
        ('cat_pipe', cat_pipe, pipe_cfg['cat_cols'])
    ])

    pipeline = Pipeline(steps=[('preprocessor', feat_pipe),
                               ('model', LGBMClassifier(random_state=0))])

    return pipeline
    
# Create the classification model training pipeline.
pipeline = create_classification_pipeline(X_train_original)

# Train the model.
model = pipeline.fit(X_train_original, y_train)

# Import the RAI dashboard components.
from raiwidgets import ResponsibleAIDashboard
from responsibleai import RAIInsights

# Define the RAIInsights object.
from responsibleai.feature_metadata import FeatureMetadata
feature_metadata = FeatureMetadata(categorical_features=categorical_features, dropped_features=[])
rai_insights = RAIInsights(model, train_data, test_data_sample, target_feature, 'classification',
                           feature_metadata=feature_metadata)

# Add the error analysis component.
rai_insights.error_analysis.add()

# Perform the RAI computation.
rai_insights.compute()

from raiutils.cohort import Cohort, CohortFilter, CohortFilterMethods
import os
from urllib.parse import urlparse

# Age is less than 65 and hours-per-week is greater than 40.
cohort_filter_age = CohortFilter(
    method=CohortFilterMethods.METHOD_LESS,
    arg=[65],
    column='age')
cohort_filter_hours_per_week = CohortFilter(
    method=CohortFilterMethods.METHOD_GREATER,
    arg=[40],
    column='hours-per-week')

user_cohort_age_and_hours_per_week = Cohort(name='Cohort Age and Hours-Per-Week')
user_cohort_age_and_hours_per_week.add_cohort_filter(cohort_filter_age)
user_cohort_age_and_hours_per_week.add_cohort_filter(cohort_filter_hours_per_week)

# Marital status is "Never-married" or "Divorced".
cohort_filter_marital_status = CohortFilter(
    method=CohortFilterMethods.METHOD_INCLUDES,
    arg=["Never-married", "Divorced"],
    column='marital-status')

user_cohort_marital_status = Cohort(name='Cohort Marital-Status')
user_cohort_marital_status.add_cohort_filter(cohort_filter_marital_status)

# Index is less than 20.
cohort_filter_index = CohortFilter(
    method=CohortFilterMethods.METHOD_LESS,
    arg=[20],
    column='Index')

user_cohort_index = Cohort(name='Cohort Index')
user_cohort_index.add_cohort_filter(cohort_filter_index)

# Predicted Y is >50K.
cohort_filter_predicted_y = CohortFilter(
    method=CohortFilterMethods.METHOD_INCLUDES,
    arg=['>50K'],
    column='Predicted Y')

user_cohort_predicted_y = Cohort(name='Cohort Predicted Y')
user_cohort_predicted_y.add_cohort_filter(cohort_filter_predicted_y)

# True Y is >50K.
cohort_filter_true_y = CohortFilter(
    method=CohortFilterMethods.METHOD_INCLUDES,
    arg=['>50K'],
    column='True Y')

user_cohort_true_y = Cohort(name='Cohort True Y')
user_cohort_true_y.add_cohort_filter(cohort_filter_true_y)

cohort_list = [user_cohort_age_and_hours_per_week,
               user_cohort_marital_status,
               user_cohort_index,
               user_cohort_predicted_y,
               user_cohort_true_y]

# Create the Responsible AI dashboard.
metric_frame_tf = ResponsibleAIDashboard(rai_insights, cohort_list=cohort_list, feature_flights="dataBalanceExperience")

# Set the URL for redirection.
metric_frame_tf.config['baseUrl'] =  'https://{}-proxy-{}.dsw-gateway-{}.data.aliyun.com'.format(
    os.environ.get('JUPYTER_NAME').replace("dsw-",""),
    urlparse(metric_frame_tf.config['baseUrl']).port,
    os.environ.get('dsw_region') )

[2024-05-29 11:04:57,458] WARNING in __init__: WebSocket transport not available. Install gevent-websocket for improved performance.

    ResponsibleAI started at http://localhost:8704