Train Classifier — mlTrainClassifier

Fit a final classification model for scoring new rows.

What it does

Connect training rows to in. The model output is a one-row reference, not the training data or a live Python estimator. It records mlflow_run_id, model_uri, task_type, model_type, target_column, feature_columns_json and model_config_json. Run metadata contains the model URI, run ID and the training metrics described below.

Runtime fits a scikit-learn pipeline, checks its serialized size and saves it to MLflow. If saving fails, the node fails rather than returning a usable model reference. Preview skips fitting and logging and emits a placeholder with null run ID and URI; configuration and schema checks can still fail during preview.

Use the purple model wire with Predict, then evaluate held-out labels with Evaluate. Supported built-in model types are logistic_regression, random_forest_classifier, svm_classifier, knn_classifier, xgboost_classifier and lightgbm_classifier. The last two need their optional libraries (pip install "ciaren[ml]"). Installed plugins can add model types; follow that provider's requirements.

Training metadata reports train_accuracy and train_f1_weighted on the rows used to fit the model. Those are training scores, not held-out evaluation. For fold-based model comparison, use an unfitted Classifier Model with Cross-Validate.

Configuration

Omitted or empty features select all columns except the target. The target cannot also be a feature; exclude customer IDs explicitly.

Preprocessing and limits

With omitted or empty preprocessing, numeric features use median imputation and standard scaling. Categorical features use most-frequent imputation and one-hot encoding with unknown categories ignored. These steps are fitted on this node's training rows and travel inside the saved pipeline.

For a nonempty preprocessing object, supply numeric_columns and/or categorical_columns: absent lists are empty and columns outside those lists are dropped. If both lists are empty, preprocessing is omitted and the raw selected features reach the estimator. Numeric options are numeric_strategy (standard_scaler, minmax_scaler, robust_scaler, or another value to omit scaling), impute_numeric (default median) and impute_categorical (default most_frequent).

Runtime requires at least ten rows and warns below fifty. Default host limits are 5,000,000 training rows, 500 selected features and 500 MB of serialized model data. Row and feature limits apply before fitting; model size is checked after fitting and before saving. Configure them with CIAREN_ML_MAX_TRAINING_ROWS, CIAREN_ML_MAX_FEATURE_COLUMNS and CIAREN_ML_MAX_MODEL_SIZE_MB. The default hyperparameter numeric bound is 100,000 (CIAREN_ML_MAX_HYPERPARAMETER_VALUE).

MLflow tracking defaults to ./mlruns; set CIAREN_MLFLOW_TRACKING_URI for a configured store. Load only trusted artifacts: MLflow/joblib deserialization can execute Python code, and URI/path checks do not sandbox that code.

Generated Python code

Download the customer sample CSV and save it as customers.csv beside the script. The sample has 16 rows; Train/Test Split uses test_size=0.25 and seed=42 to keep 12 training rows separate from four held-out rows. Install Ciaren with its ML dependencies to run the scripts. Polars exports cross into pandas/scikit-learn for fitting.

These are complete exports from the flow generator. They fit a pipeline in memory; they do not create an MLflow run, save a model artifact, reproduce run metadata metrics or enforce Ciaren's runtime row/feature/model-size guards. The editor's trained-model reference becomes the actual pipeline variable in the script. To retain an exported model, add your own trusted persistence step.

The example fits a 20-tree random forest on churn, with tenure, monthly_charges and support_calls as predictors. The split is stratified by churn. Connect train to Train Classifier, its model wire to Predict, and test to Predict's data input. Predict writes four rows to train-classifier.csv; predictions are 0, 1, 0, 1 in customer order 8, 3, 14, 13. The sample is too small to establish real-world model quality.

The Train configuration is:

{
  "model_type": "random_forest_classifier",
  "target_column": "churn",
  "feature_columns": [
    "tenure",
    "monthly_charges",
    "support_calls"
  ],
  "hyperparameters": {
    "n_estimators": 20
  },
  "seed": 42
}

pandas

import pandas as pd
import joblib
import mlflow.sklearn
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler

df_customers = pd.read_csv('customers.csv')
df_1, df_2 = train_test_split(df_customers, test_size=0.25, random_state=42, stratify=df_customers['churn'])
df_1 = df_1.reset_index(drop=True)
df_2 = df_2.reset_index(drop=True)
_features = ['tenure', 'monthly_charges', 'support_calls']
_X = df_1[_features]
_numeric = [c for c in _features if pd.api.types.is_numeric_dtype(_X[c])]
_categorical = [c for c in _features if c not in _numeric]
_transformers = []
if _numeric:
    _transformers.append(('num', Pipeline([('impute', SimpleImputer(strategy='median')), ('scale', StandardScaler())]), _numeric))
if _categorical:
    _transformers.append(('cat', Pipeline([('impute', SimpleImputer(strategy='most_frequent')), ('encode', OneHotEncoder(handle_unknown='ignore'))]), _categorical))
_preprocessor = ColumnTransformer(_transformers, remainder='drop')
_y = df_1['churn']
df_3 = Pipeline([('preprocessor', _preprocessor), ('model', RandomForestClassifier(n_estimators=20, random_state=42))])
df_3.fit(_X, _y)
df_4 = df_2.copy()
_model_features = list(getattr(df_3, 'feature_names_in_', df_2.columns))
df_4['prediction'] = df_3.predict(df_2[_model_features])
df_4.to_csv('train-classifier.csv', index=False)

polars

import polars as pl
import joblib
import mlflow.sklearn
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler

df_customers = pl.read_csv('customers.csv')
_eager_1 = df_customers.to_pandas()
_eager_2, _eager_3 = train_test_split(_eager_1, test_size=0.25, random_state=42, stratify=_eager_1['churn'])
_eager_2 = _eager_2.reset_index(drop=True)
_eager_3 = _eager_3.reset_index(drop=True)
df_1 = pl.from_pandas(_eager_2)
df_2 = pl.from_pandas(_eager_3)
_eager_4 = df_1.to_pandas()
_features = ['tenure', 'monthly_charges', 'support_calls']
_X = _eager_4[_features]
_numeric = [c for c in _features if pd.api.types.is_numeric_dtype(_X[c])]
_categorical = [c for c in _features if c not in _numeric]
_transformers = []
if _numeric:
    _transformers.append(('num', Pipeline([('impute', SimpleImputer(strategy='median')), ('scale', StandardScaler())]), _numeric))
if _categorical:
    _transformers.append(('cat', Pipeline([('impute', SimpleImputer(strategy='most_frequent')), ('encode', OneHotEncoder(handle_unknown='ignore'))]), _categorical))
_preprocessor = ColumnTransformer(_transformers, remainder='drop')
_y = _eager_4['churn']
_eager_5 = Pipeline([('preprocessor', _preprocessor), ('model', RandomForestClassifier(n_estimators=20, random_state=42))])
_eager_5.fit(_X, _y)
_eager_6 = df_2.to_pandas()
_eager_7 = _eager_6.copy()
_model_features = list(getattr(_eager_5, 'feature_names_in_', _eager_6.columns))
_eager_7['prediction'] = _eager_5.predict(_eager_6[_model_features])
df_3 = pl.from_pandas(_eager_7)
df_3.write_csv('train-classifier.csv')

Tips and common mistakes

• Split before training. Fitted preprocessing stays inside the model rather than being refitted independently on the held-out branch.
• Probability support depends on the estimator. For svm_classifier, request probability=true in hyperparameters if you need predict_proba.
• Training scores can be optimistic; use held-out evaluation or cross-validation.
• Save failures mean no usable artifact was returned. On Windows, a long MLflow artifact path can cause this; use a shorter tracking path and rerun.

See also

• Predict
• Evaluate
• Classifier Model
• Feature Importance
• ML quick start