Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
# Add a large dataset to DVC tracking
dvc add data/raw/survey_2023.csv
# This creates:# - data/raw/survey_2023.csv.dvc (commit this to Git)# - .gitignore updated to ignore the actual CSV
git add data/raw/survey_2023.csv.dvc data/raw/.gitignore
git commit -m "Add survey 2023 dataset to DVC"# Push data to remote
dvc push
# Later: reproduce from another machine
git clone https://github.com/org/my-research-project
cd my-research-project
dvc pull # downloads data from remote
# Run the full pipeline
dvc repro
# View metrics
dvc metrics show
# Visualize the DAG
dvc dag
Step 3: Experiment Tracking and Comparison
# File: scripts/run_experiments.py"""Run multiple experiments varying hyperparameters."""import subprocess
import json
import yaml
from pathlib import Path
import pandas as pd
defrun_dvc_experiment(params_override, exp_name=None):
"""Run a DVC experiment with given parameter overrides.
Args:
params_override: dict of param_path → value (e.g., "train.n_estimators" → 200)
exp_name: optional experiment name
Returns:
dict with command result
"""
cmd = ["dvc", "exp", "run"]
if exp_name:
cmd.extend(["--name", exp_name])
for param_path, value in params_override.items():
cmd.extend(["--set-param", f"{param_path}={value}"])
print(f"Running: {' '.join(cmd)}")
result = subprocess.run(cmd, capture_output=True, text=True)
return {
"returncode": result.returncode,
"stdout": result.stdout,
"stderr": result.stderr,
"success": result.returncode == 0,
}
defget_experiments_table():
"""Retrieve experiment comparison table from DVC."""
result = subprocess.run(
["dvc", "exp", "show", "--csv"],
capture_output=True, text=True
)
if result.returncode == 0:
import io
return pd.read_csv(io.StringIO(result.stdout))
return pd.DataFrame()
# Define experiment grid
experiments = [
{
"name": "rf-100-depth5",
"params": {
"train.model_type": "random_forest",
"train.n_estimators": 100,
"train.max_depth": 5,
}
},
{
"name": "rf-200-depth8",
"params": {
"train.model_type": "random_forest",
"train.n_estimators": 200,
"train.max_depth": 8,
}
},
{
"name": "gb-100-depth4",
"params": {
"train.model_type": "gradient_boosting",
"train.n_estimators": 100,
"train.max_depth": 4,
}
},
]
print("=== DVC Experiment Grid ===")
for exp in experiments:
print(f"\nExperiment: {exp['name']}")
for k, v in exp['params'].items():
print(f" {k} = {v}")
# In a real workflow, uncomment:# for exp in experiments:# result = run_dvc_experiment(exp["params"], exp_name=exp["name"])# print(f" {'OK' if result['success'] else 'FAILED'}: {exp['name']}")# Load results from metrics files directly (as DVC substitute)
metrics_files = list(Path("metrics").glob("*.json"))
results = []
for f in metrics_files:
withopen(f) as fp:
data = json.load(fp)
ifisinstance(data, dict) and"test_rmse"in data:
data["file"] = str(f)
results.append(data)
if results:
df_results = pd.DataFrame(results)
print("\n=== Current Metrics ===")
print(df_results.to_string(index=False))
Advanced Usage
DVC Data Registry Pattern
# Register shared datasets accessible to all team projects# In a central "data-registry" repo
dvc add data/gold/benchmark_dataset_v2.parquet
git commit -am "Add benchmark dataset v2"
git tag -a "benchmark-v2.0" -m "Benchmark dataset version 2"
dvc push
# In a downstream project
dvc import git@github.com:org/data-registry.git \
data/gold/benchmark_dataset_v2.parquet \
-o data/benchmark.parquet
# Get updates when registry is updated
dvc update benchmark.parquet.dvc
Parameterized Pipeline via Python
# File: scripts/parametric_run.py"""Generate DVC pipeline configurations programmatically."""import yaml
from pathlib import Path
from itertools import product
defgenerate_dvc_yaml(model_types, n_estimators_list):
"""Generate dvc.yaml with multiple training configurations."""
stages = {}
for model, n_est in product(model_types, n_estimators_list):
stage_name = f"train_{model}_{n_est}"
stages[stage_name] = {
"cmd": f"python src/train.py --model {model} --n-estimators {n_est}",
"deps": ["data/processed/X_train.npy", "src/train.py"],
"outs": [f"models/{model}_{n_est}/model.pkl"],
"metrics": [{f"metrics/{model}_{n_est}_metrics.json": {"cache": False}}],
"params": ["params.yaml:train.random_seed"],
}
dvc_config = {"stages": stages}
withopen("dvc_grid.yaml", "w") as f:
yaml.dump(dvc_config, f, default_flow_style=False)
print(f"Generated dvc_grid.yaml with {len(stages)} stages")
return stages
stages = generate_dvc_yaml(
model_types=["random_forest", "gradient_boosting"],
n_estimators_list=[50, 100, 200]
)
# Run specific stage# dvc repro -f dvc_grid.yaml dvc_grid:train_random_forest_100
Integration with MLflow
# File: src/train_with_mlflow.py"""Train model with MLflow tracking alongside DVC."""import numpy as np
import yaml
import pickle
import json
import os
from pathlib import Path
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score, mean_squared_error
MLFLOW_TRACKING_URI = os.getenv("MLFLOW_TRACKING_URI", "http://localhost:5000")
deftrain_with_tracking():
withopen("params.yaml") as f:
params = yaml.safe_load(f)
X_train = np.load("data/processed/X_train.npy")
y_train = np.load("data/processed/y_train.npy")
X_test = np.load("data/processed/X_test.npy")
y_test = np.load("data/processed/y_test.npy")
cfg = params["train"]
model = RandomForestRegressor(
n_estimators=cfg.get("n_estimators", 100),
max_depth=cfg.get("max_depth", 5),
random_state=cfg.get("random_seed", 42)
)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
metrics = {
"test_rmse": float(np.sqrt(mean_squared_error(y_test, y_pred))),
"test_r2": float(r2_score(y_test, y_pred)),
}
try:
import mlflow
mlflow.set_tracking_uri(MLFLOW_TRACKING_URI)
with mlflow.start_run(run_name="dvc_experiment"):
mlflow.log_params(cfg)
mlflow.log_metrics(metrics)
mlflow.sklearn.log_model(model, "model")
print(f"Logged to MLflow at {MLFLOW_TRACKING_URI}")
except ImportError:
print("MLflow not installed — logging to JSON only")
except Exception as e:
print(f"MLflow logging failed ({e}) — continuing with JSON")
Path("metrics").mkdir(exist_ok=True)
withopen("metrics/test_metrics.json", "w") as f:
json.dump(metrics, f, indent=2)
Path("models").mkdir(exist_ok=True)
withopen("models/model.pkl", "wb") as f:
pickle.dump(model, f)
print(f"Test RMSE: {metrics['test_rmse']:.4f}, R²: {metrics['test_r2']:.4f}")
if __name__ == "__main__":
train_with_tracking()
Troubleshooting
Problem
Cause
Fix
dvc: command not found
DVC not installed
pip install dvc; ensure venv is activated
ERROR: Git is not initialized
Running dvc init outside git repo
git init first, then dvc init
Remote push fails (S3)
Missing AWS credentials
Set AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY env vars
Pipeline doesn't re-run
DVC thinks stage is up-to-date
dvc repro --force to override cache
Stage skipped despite code change
Script not in deps list
Add script file to deps: in dvc.yaml
dvc.lock conflict (git merge)
Parallel pipeline runs
Resolve manually; keep the run with better metrics
