def get_sample(src: DataItem, sample: int, label: str, reader=None):
"""generate data sample to be split (candidate for mlrun)
Returns features matrix and header (x), and labels (y)
:param src: data artifact
:param sample: sample size from data source, use negative
integers to sample randomly, positive to
sample consecutively from the first row
:param label: label column title
"""
table = src.as_df()
# get sample
if (sample == -1) or (sample >= 1):
# get all rows, or contiguous sample starting at row 1.
raw = table.dropna()
labels = raw.pop(label)
raw = raw.iloc[:sample, :]
labels = labels.iloc[:sample]
else:
# grab a random sample
raw = table.dropna().sample(sample * -1)
labels = raw.pop(label)
return raw, labels, raw.columns.values
def xgb_test(
context,
models_path: DataItem,
test_set: DataItem,
label_column: str,
plots_dest: str = "plots",
default_model: str = "model.pkl",
) -> None:
"""Test one or more classifier models against held-out dataset
Using held-out test features, evaluates the peformance of the estimated model
Can be part of a kubeflow pipeline as a test step that is run post EDA and
training/validation cycles
:param context: the function context
:param models_path: model artifact to be tested
:param test_set: test features and labels
:param label_column: column name for ground truth labels
:param plots_dest: dir for test plots
:param default_model: 'model.pkl', default model artifact file name
"""
xtest = test_set.as_df()
ytest = xtest.pop(label_column)
try:
model_file, model_obj, _ = get_model(models_path.url, suffix=".pkl")
model_obj = load(open(model_file, "rb"))
except Exception as a:
raise Exception("model location likely misspecified")
eval_metrics = eval_model_v2(context, xtest, ytest.values, model_obj)
def test_classifier(
context,
models_path: DataItem,
test_set: DataItem,
label_column: str,
score_method: str = "micro",
plots_dest: str = "",
model_evaluator=None,
default_model: str = "model.pkl",
predictions_column: str = "yscore",
model_update=True,
) -> None:
"""Test one or more classifier models against held-out dataset
Using held-out test features, evaluates the peformance of the estimated model
Can be part of a kubeflow pipeline as a test step that is run post EDA and
training/validation cycles
:param context: the function context
:param models_path: artifact models representing a file or a folder
:param test_set: test features and labels
:param label_column: column name for ground truth labels
:param score_method: for multiclass classification
:param plots_dest: dir for test plots
:param model_evaluator: NOT IMPLEMENTED: specific method to generate eval, passed in as string
or available in this folder
:param predictions_column: column name for the predictions column on the resulted artifact
:param model_update: (True) update model, when running as stand alone no need in update
"""
xtest = test_set.as_df()
ytest = xtest.pop(label_column)
try:
model_file, model_obj, _ = get_model(models_path, suffix=".pkl")
model_obj = load(open(model_file, "rb"))
except Exception as a:
raise Exception("model location likely specified")
extra_data = eval_model_v2(context, xtest, ytest.values, model_obj)
if model_obj and model_update == True:
update_model(
models_path,
extra_data=extra_data,
metrics=context.results,
key_prefix="validation-",
)
y_hat = model_obj.predict(xtest)
if y_hat.ndim == 1 or y_hat.shape[1] == 1:
score_names = [predictions_column]
else:
score_names = [
f"{predictions_column}_" + str(x) for x in range(y_hat.shape[1])
]
df = pd.concat(
[xtest, ytest, pd.DataFrame(y_hat, columns=score_names)], axis=1)
context.log_dataset("test_set_preds", df=df, format="parquet", index=False)
def cox_test(
context,
models_path: DataItem,
test_set: DataItem,
label_column: str,
plots_dest: str = "plots",
model_evaluator=None,
) -> None:
"""Test one or more classifier models against held-out dataset
Using held-out test features, evaluates the peformance of the estimated model
Can be part of a kubeflow pipeline as a test step that is run post EDA and
training/validation cycles
:param context: the function context
:param model_file: model artifact to be tested
:param test_set: test features and labels
:param label_column: column name for ground truth labels
:param score_method: for multiclass classification
:param plots_dest: dir for test plots
:param model_evaluator: WIP: specific method to generate eval, passed in as string
or available in this folder
"""
xtest = test_set.as_df()
ytest = xtest.pop(label_column)
model_file, model_obj, _ = get_model(models_path.url, suffix=".pkl")
model_obj = load(open(str(model_file), "rb"))
try:
if not model_evaluator:
eval_metrics = eval_class_model(context, xtest, ytest, model_obj)
model_plots = eval_metrics.pop("plots")
model_tables = eval_metrics.pop("tables")
for plot in model_plots:
context.log_artifact(plot,
local_path=f"{plots_dest}/{plot.key}.html")
for tbl in model_tables:
context.log_artifact(tbl,
local_path=f"{plots_dest}/{plot.key}.csv")
context.log_results(eval_metrics)
except:
context.log_dataset("cox-test-summary",
df=model_obj.summary,
index=True,
format="csv")
context.logger.info("cox tester not implemented")
def open_archive(
context: MLClientCtx,
archive_url: DataItem,
subdir: str = "content",
key: str = "content",
target_path: str = None,
):
"""Open a file/object archive into a target directory
Currently supports zip and tar.gz
:param context: function execution context
:param archive_url: url of archive file
:param subdir: path within artifact store where extracted files
are stored
:param key: key of archive contents in artifact store
:param target_path: file system path to store extracted files (use either this or subdir)
"""
os.makedirs(target_path or subdir, exist_ok=True)
archive_url = archive_url.local()
if archive_url.endswith("gz"):
with tarfile.open(archive_url, mode="r|gz") as ref:
ref.extractall(target_path or subdir)
elif archive_url.endswith("zip"):
with zipfile.ZipFile(archive_url, "r") as ref:
ref.extractall(target_path or subdir)
else:
raise ValueError(f"unsupported archive type in {archive_url}")
kwargs = {}
if target_path:
kwargs = {"target_path": target_path}
else:
kwargs = {"local_path": subdir}
context.log_artifact(key, **kwargs)
def load_dask(
context: MLClientCtx,
src_data: DataItem,
dask_key: str = "dask_key",
inc_cols: Optional[List[str]] = None,
index_cols: Optional[List[str]] = None,
dask_persist: bool = True,
refresh_data: bool = True,
scheduler_key: str = "scheduler"
) -> None:
"""Load dataset into an existing dask cluster
dask jobs define the dask client parameters at the job level, this method will raise an error if no client is detected.
:param context: the function context
:param src_data: url of the data file or partitioned dataset as either
artifact DataItem, string, or path object (similar to
pandas read_csv)
:param dask_key: destination key of data on dask cluster and artifact store
:param inc_cols: include only these columns (very fast)
:param index_cols: list of index column names (can be a long-running process)
:param dask_persist: (True) should the data be persisted (through the `client.persist` op)
:param refresh_data: (False) if the dask_key already exists in the dask cluster, this will
raise an Exception. Set to True to replace the existing cluster data.
:param scheduler_key: (scheduler) the dask scheduler configuration, json also logged as an artifact
"""
if hasattr(context, "dask_client"):
dask_client = context.dask_client
else:
raise Exception("a dask client was not found in the execution context")
df = src_data.as_df(df_module=dd)
if dask_persist:
df = dask_client.persist(df)
if dask_client.datasets and dask_key in dask_client.datasets:
dask_client.unpublish_dataset(dask_key)
dask_client.publish_dataset(df, name=dask_key)
if context:
context.dask_client = dask_client
# share the scheduler, whether data is persisted or not
dask_client.write_scheduler_file(scheduler_key + ".json")
# we don't use log_dataset here until it can take into account
# dask origin and apply dask describe.
context.log_artifact(scheduler_key, local_path=scheduler_key + ".json")
def pandas_profiling_report(
context: MLClientCtx,
data: DataItem,
) -> None:
"""Create a Pandas Profiling Report for a dataset.
:param context: the function context
:param data: Dataset to create report for
"""
df = data.as_df()
profile = df.profile_report(title="Pandas Profiling Report")
context.log_artifact(
"Pandas Profiling Report",
body=profile.to_html(),
local_path="pandas_profiling_report.html",
)
def model_server_tester(context,
table: DataItem,
addr: str,
label_column: str = "label",
model: str = '',
match_err: bool = False,
rows: int = 20):
""" Test a model server
:param table: csv/parquet table with test data
:param addr: function address/url
:param label_column: name of the label column in table
:param model: tested model name
:param match_err: raise error on validation (require proper test set)
:param rows: number of rows to use from test set
"""
table = table.as_df()
y_list = table.pop(label_column).values.tolist()
context.logger.info(f'testing with dataset against {addr}, model: {model}')
if rows and rows < table.shape[0]:
table = table.sample(rows)
count = err_count = match = 0
times = []
for x, y in zip(table.values, y_list):
count += 1
event_data = json.dumps({"inputs": [x.tolist()]})
had_err = False
try:
start = datetime.now()
resp = requests.put(f'{addr}/v2/models/{model}/infer',
json=event_data)
if not resp.ok:
context.logger.error(f'bad function resp!!\n{resp.text}')
err_count += 1
continue
times.append((datetime.now() - start).microseconds)
except OSError as err:
context.logger.error(
f'error in request, data:{event_data}, error: {err}')
err_count += 1
continue
resp_data = resp.json()
print(resp_data)
y_resp = resp_data['outputs'][0]
if y == y_resp:
match += 1
context.log_result('total_tests', count)
context.log_result('errors', err_count)
context.log_result('match', match)
if count - err_count > 0:
times_arr = np.array(times)
context.log_result('avg_latency', int(np.mean(times_arr)))
context.log_result('min_latency', int(np.amin(times_arr)))
context.log_result('max_latency', int(np.amax(times_arr)))
chart = ChartArtifact('latency', header=['Test', 'Latency (microsec)'])
for i in range(len(times)):
chart.add_row([i + 1, int(times[i])])
context.log_artifact(chart)
context.logger.info(
f'run {count} tests, {err_count} errors and {match} match expected value'
)
if err_count:
raise ValueError(f'failed on {err_count} tests of {count}')
if match_err and match != count:
raise ValueError(f'only {match} results match out of {count}')
def summarize(
context: MLClientCtx,
table: DataItem,
label_column: str = None,
class_labels: List[str] = [],
plot_hist: bool = True,
plots_dest: str = "plots",
update_dataset=False,
) -> None:
"""Summarize a table
:param context: the function context
:param table: MLRun input pointing to pandas dataframe (csv/parquet file path)
:param label_column: ground truth column label
:param class_labels: label for each class in tables and plots
:param plot_hist: (True) set this to False for large tables
:param plots_dest: destination folder of summary plots (relative to artifact_path)
:param update_dataset: when the table is a registered dataset update the charts in-place
"""
df = table.as_df()
header = df.columns.values
extra_data = {}
try:
gcf_clear(plt)
snsplt = sns.pairplot(df, hue=label_column) # , diag_kws={"bw": 1.5})
extra_data["histograms"] = context.log_artifact(
PlotArtifact("histograms", body=plt.gcf()),
local_path=f"{plots_dest}/hist.html",
db_key=False,
)
except Exception as e:
context.logger.error(
f"Failed to create pairplot histograms due to: {e}")
try:
gcf_clear(plt)
plot_cols = 3
plot_rows = int((len(header) - 1) / plot_cols) + 1
fig, ax = plt.subplots(plot_rows, plot_cols, figsize=(15, 4))
fig.tight_layout(pad=2.0)
for i in range(plot_rows * plot_cols):
if i < len(header):
sns.violinplot(
x=df[header[i]],
ax=ax[int(i / plot_cols)][i % plot_cols],
orient="h",
width=0.7,
inner="quartile",
)
else:
fig.delaxes(ax[int(i / plot_cols)][i % plot_cols])
i += 1
extra_data["violin"] = context.log_artifact(
PlotArtifact("violin", body=plt.gcf(), title="Violin Plot"),
local_path=f"{plots_dest}/violin.html",
db_key=False,
)
except Exception as e:
context.logger.warn(
f"Failed to create violin distribution plots due to: {e}")
if label_column:
labels = df.pop(label_column)
imbtable = labels.value_counts(normalize=True).sort_index()
try:
gcf_clear(plt)
balancebar = imbtable.plot(kind="bar",
title="class imbalance - labels")
balancebar.set_xlabel("class")
balancebar.set_ylabel("proportion of total")
extra_data["imbalance"] = context.log_artifact(
PlotArtifact("imbalance", body=plt.gcf()),
local_path=f"{plots_dest}/imbalance.html",
)
except Exception as e:
context.logger.warn(
f"Failed to create class imbalance plot due to: {e}")
context.log_artifact(
TableArtifact("imbalance-weights-vec",
df=pd.DataFrame({"weights": imbtable})),
local_path=f"{plots_dest}/imbalance-weights-vec.csv",
db_key=False,
)
tblcorr = df.corr()
mask = np.zeros_like(tblcorr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
dfcorr = pd.DataFrame(data=tblcorr, columns=header, index=header)
dfcorr = dfcorr[
np.arange(dfcorr.shape[0])[:, None] > np.arange(dfcorr.shape[1])]
context.log_artifact(
TableArtifact("correlation-matrix", df=tblcorr, visible=True),
local_path=f"{plots_dest}/correlation-matrix.csv",
db_key=False,
)
try:
gcf_clear(plt)
ax = plt.axes()
sns.heatmap(tblcorr, ax=ax, mask=mask, annot=False, cmap=plt.cm.Reds)
ax.set_title("features correlation")
extra_data["correlation"] = context.log_artifact(
PlotArtifact("correlation",
body=plt.gcf(),
title="Correlation Matrix"),
local_path=f"{plots_dest}/corr.html",
db_key=False,
)
except Exception as e:
context.logger.warn(
f"Failed to create features correlation plot due to: {e}")
gcf_clear(plt)
if update_dataset and table.meta and table.meta.kind == "dataset":
from mlrun.artifacts import update_dataset_meta
update_dataset_meta(table.meta, extra_data=extra_data)
def describe_spark(context: MLClientCtx,
dataset: DataItem,
artifact_path,
bins: int = 30,
describe_extended: bool = True):
location = dataset.local()
spark = SparkSession.builder.appName("Spark job").getOrCreate()
df = spark.read.csv(location, header=True, inferSchema=True)
kwargs = []
float_cols = [
item[0] for item in df.dtypes
if item[1].startswith('float') or item[1].startswith('double')
]
if describe_extended == True:
table, variables, freq = describe(df, bins, float_cols, kwargs)
tbl_1 = variables.reset_index()
if len(freq) != 0:
tbl_2 = pd.DataFrame.from_dict(
freq, orient="index").sort_index().stack().reset_index()
tbl_2.columns = ['col', 'key', 'val']
tbl_2['Merged'] = [{
key: val
} for key, val in zip(tbl_2.key, tbl_2.val)]
tbl_2 = tbl_2.groupby(
'col',
as_index=False).agg(lambda x: tuple(x))[['col', 'Merged']]
summary = pd.merge(tbl_1,
tbl_2,
how='left',
left_on='index',
right_on='col')
else:
summary = tbl_1
context.log_dataset("summary_stats",
df=summary,
format="csv",
index=False,
artifact_path=context.artifact_subpath('data'))
context.log_results(table)
else:
tbl_1 = df.describe().toPandas()
summary = tbl_1.T
context.log_dataset("summary_stats",
df=summary,
format="csv",
index=False,
artifact_path=context.artifact_subpath('data'))
spark.stop()
def train_model(context: MLClientCtx,
dataset: DataItem,
model_pkg_class: str,
label_column: str = "label",
train_validation_size: float = 0.75,
sample: float = 1.0,
models_dest: str = "models",
test_set_key: str = "test_set",
plots_dest: str = "plots",
dask_key: str = "dask_key",
dask_persist: bool = False,
scheduler_key: str = '',
file_ext: str = "parquet",
random_state: int = 42) -> None:
"""
Train a sklearn classifier with Dask
:param context: Function context.
:param dataset: Raw data file.
:param model_pkg_class: Model to train, e.g, "sklearn.ensemble.RandomForestClassifier",
or json model config.
:param label_column: (label) Ground-truth y labels.
:param train_validation_size: (0.75) Train validation set proportion out of the full dataset.
:param sample: (1.0) Select sample from dataset (n-rows/% of total), randomzie rows as default.
:param models_dest: (models) Models subfolder on artifact path.
:param test_set_key: (test_set) Mlrun db key of held out data in artifact store.
:param plots_dest: (plots) Plot subfolder on artifact path.
:param dask_key: (dask key) Key of dataframe in dask client "datasets" attribute.
:param dask_persist: (False) Should the data be persisted (through the `client.persist`)
:param scheduler_key: (scheduler) Dask scheduler configuration, json also logged as an artifact.
:param file_ext: (parquet) format for test_set_key hold out data
:param random_state: (42) sklearn seed
"""
if scheduler_key:
client = Client(scheduler_key)
else:
client = Client()
context.logger.info("Read Data")
df = dataset.as_df(df_module=dd)
context.logger.info("Prep Data")
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
df = df.select_dtypes(include=numerics)
if df.isna().any().any().compute() == True:
raise Exception('NAs valus found')
df_header = df.columns
df = df.sample(frac=sample).reset_index(drop=True)
encoder = LabelEncoder()
encoder = encoder.fit(df[label_column])
X = df.drop(label_column, axis=1).to_dask_array(lengths=True)
y = encoder.transform(df[label_column])
classes = df[label_column].drop_duplicates() # no unique values in dask
classes = [str(i) for i in classes]
context.logger.info("Split and Train")
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, train_size=train_validation_size, random_state=random_state)
scaler = StandardScaler()
scaler = scaler.fit(X_train)
X_train_transformed = scaler.transform(X_train)
X_test_transformed = scaler.transform(X_test)
model_config = gen_sklearn_model(model_pkg_class,
context.parameters.items())
model_config["FIT"].update({"X": X_train_transformed, "y": y_train})
ClassifierClass = create_class(model_config["META"]["class"])
model = ClassifierClass(**model_config["CLASS"])
with joblib.parallel_backend("dask"):
model = model.fit(**model_config["FIT"])
artifact_path = context.artifact_subpath(models_dest)
plots_path = context.artifact_subpath(models_dest, plots_dest)
context.logger.info("Evaluate")
extra_data_dict = {}
for report in (ROCAUC, ClassificationReport, ConfusionMatrix):
report_name = str(report.__name__)
plt.cla()
plt.clf()
plt.close()
viz = report(model, classes=classes, per_class=True, is_fitted=True)
viz.fit(X_train_transformed,
y_train) # Fit the training data to the visualizer
viz.score(X_test_transformed,
y_test.compute()) # Evaluate the model on the test data
plot = context.log_artifact(PlotArtifact(report_name,
body=viz.fig,
title=report_name),
db_key=False)
extra_data_dict[str(report)] = plot
if report_name == 'ROCAUC':
context.log_results({
"micro": viz.roc_auc.get("micro"),
"macro": viz.roc_auc.get("macro")
})
elif report_name == 'ClassificationReport':
for score_name in viz.scores_:
for score_class in viz.scores_[score_name]:
context.log_results({
score_name + "-" + score_class:
viz.scores_[score_name].get(score_class)
})
viz = FeatureImportances(model,
classes=classes,
per_class=True,
is_fitted=True,
labels=df_header.delete(
df_header.get_loc(label_column)))
viz.fit(X_train_transformed, y_train)
viz.score(X_test_transformed, y_test)
plot = context.log_artifact(PlotArtifact("FeatureImportances",
body=viz.fig,
title="FeatureImportances"),
db_key=False)
extra_data_dict[str("FeatureImportances")] = plot
plt.cla()
plt.clf()
plt.close()
context.logger.info("Log artifacts")
artifact_path = context.artifact_subpath(models_dest)
plots_path = context.artifact_subpath(models_dest, plots_dest)
context.set_label('class', model_pkg_class)
context.log_model("model",
body=dumps(model),
artifact_path=artifact_path,
model_file="model.pkl",
extra_data=extra_data_dict,
metrics=context.results,
labels={"class": model_pkg_class})
context.log_artifact("standard_scaler",
body=dumps(scaler),
artifact_path=artifact_path,
model_file="scaler.gz",
label="standard_scaler")
context.log_artifact("label_encoder",
body=dumps(encoder),
artifact_path=artifact_path,
model_file="encoder.gz",
label="label_encoder")
df_to_save = delayed(np.column_stack)((X_test, y_test)).compute()
context.log_dataset(
test_set_key,
df=pd.DataFrame(df_to_save,
columns=df_header), # improve log dataset ability
format=file_ext,
index=False,
labels={"data-type": "held-out"},
artifact_path=context.artifact_subpath('data'))
context.logger.info("Done!")
def permutation_importance(
context: MLClientCtx,
model: DataItem,
dataset: DataItem,
labels: str,
figsz=(10, 5),
plots_dest: str = "plots",
fitype: str = "permute",
) -> pd.DataFrame:
"""calculate change in metric
type 'permute' uses a pre-estimated model
type 'dropcol' uses a re-estimates model
:param context: the function's execution context
:param model: a trained model
:param dataset: features and ground truths, regression targets
:param labels name of the ground truths column
:param figsz: matplotlib figure size
:param plots_dest: path within artifact store
:
"""
model_file, model_data, _ = get_model(model.url, suffix=".pkl")
model = load(open(str(model_file), "rb"))
X = dataset.as_df()
y = X.pop(labels)
header = X.columns
metric = _oob_classifier_accuracy
baseline = metric(model, X, y)
imp = []
for col in X.columns:
if fitype is "permute":
save = X[col].copy()
X[col] = np.random.permutation(X[col])
m = metric(model, X, y)
X[col] = save
imp.append(baseline - m)
elif fitype is "dropcol":
X_ = X.drop(col, axis=1)
model_ = clone(model)
#model_.random_state = random_state
model_.fit(X_, y)
o = model_.oob_score_
imp.append(baseline - o)
else:
raise ValueError(
"unknown fitype, only 'permute' or 'dropcol' permitted")
zipped = zip(imp, header)
feature_imp = pd.DataFrame(sorted(zipped),
columns=["importance", "feature"])
feature_imp.sort_values(by="importance", ascending=False, inplace=True)
plt.clf()
plt.figure(figsize=figsz)
sns.barplot(x="importance", y="feature", data=feature_imp)
plt.title(f"feature importances-{fitype}")
plt.tight_layout()
context.log_artifact(
PlotArtifact(f"feature importances-{fitype}", body=plt.gcf()),
local_path=f"{plots_dest}/feature-permutations.html",
)
context.log_dataset(f"feature-importances-{fitype}-tbl",
df=feature_imp,
index=False)
def data_clean(context: MLClientCtx,
src: DataItem,
file_ext: str = "csv",
models_dest: str = "models/encoders",
cleaned_key: str = "cleaned-data",
encoded_key: str = "encoded-data"):
df = src.as_df()
# drop columns
drop_cols_list = ["customerID", "TotalCharges"]
df.drop(drop_cols_list, axis=1, inplace=True)
# header transformations
old_cols = df.columns
rename_cols_map = {
"SeniorCitizen": "senior",
"Partner": "partner",
"Dependents": "deps",
"Churn": "labels"
}
df.rename(rename_cols_map, axis=1, inplace=True)
# add drop column to logs:
for col in drop_cols_list:
rename_cols_map.update({col: "_DROPPED_"})
# log the op
tp = os.path.join(models_dest, "preproc-column_map.json")
context.log_artifact("preproc-column_map.json",
body=json.dumps(rename_cols_map),
local_path=tp)
df = df.applymap(lambda x: "No" if str(x).startswith("No ") else x)
# encode numerical type as category bins (ordinal)
bins = [0, 12, 24, 36, 48, 60, np.inf]
labels = [0, 1, 2, 3, 4, 5]
tenure = df.tenure.copy(deep=True)
df["tenure_map"] = pd.cut(df.tenure, bins, labels=False)
tenure_map = dict(zip(bins, labels))
# save this transformation
tp = os.path.join(models_dest, "preproc-numcat_map.json")
context.log_artifact("preproc-numcat_map.json",
body=bytes(json.dumps(tenure_map).encode("utf-8")),
local_path=tp)
context.log_dataset(cleaned_key, df=df, format=file_ext, index=False)
fix_cols = [
"gender", "partner", "deps", "OnlineSecurity", "OnlineBackup",
"DeviceProtection", "TechSupport", "StreamingTV", "StreamingMovies",
"PhoneService", "MultipleLines", "PaperlessBilling", "InternetService",
"Contract", "PaymentMethod", "labels"
]
d = defaultdict(LabelEncoder)
df[fix_cols] = df[fix_cols].apply(
lambda x: d[x.name].fit_transform(x.astype(str)))
context.log_dataset(encoded_key, df=df, format=file_ext, index=False)
model_bin = dumps(d)
context.log_model("model",
body=model_bin,
artifact_path=os.path.join(context.artifact_path,
models_dest),
model_file="model.pkl")
def data_clean(
context: MLClientCtx,
src: DataItem,
file_ext: str = "csv",
models_dest: str = "models/encoders",
cleaned_key: str = "cleaned-data",
encoded_key: str = "encoded-data",
):
"""process a raw churn data file
Data has 3 states here: `raw`, `cleaned` and `encoded`
* `raw` kept by default, the pipeline begins with a raw data artifact
* `cleaned` kept for charts, presentations
* `encoded` is input for a cross validation and training function
steps (not necessarily in correct order, some parallel)
* column name maps
* deal with nans and other types of missings/junk
* label encode binary and ordinal category columns
* create category ranges from numerical columns
And finally,
* test
Why we don't one-hot-encode here? One hot encoding isn't a necessary
step for all algorithms. It can also generate a very large feature
matrix that doesn't need to be serialized (even if sparse).
So we leave one-hot-encoding for the training step.
What about scaling numerical columns? Same as why we don't one hot
encode here. Do we scale before train-test split? IMHO, no. Scaling
before splitting introduces a type of data leakage. In addition,
many estimators are completely immune to the monotonic transformations
implied by scaling, so why waste the cycles?
TODO:
* parallelize where possible
* more abstraction (more parameters, chain sklearn transformers)
* convert to marketplace function
:param context: the function execution context
:param src: an artifact or file path
:param file_ext: file type for artifacts
:param models_dest: label encoders and other preprocessing steps
should be saved together with other pipeline
models
:param cleaned_key: key of cleaned data table in artifact store
:param encoded_key: key of encoded data table in artifact store
"""
df = src.as_df()
# drop columns
drop_cols_list = ["customerID", "TotalCharges"]
df.drop(drop_cols_list, axis=1, inplace=True)
# header transformations
rename_cols_map = {
"SeniorCitizen": "senior",
"Partner": "partner",
"Dependents": "deps",
"Churn": "labels",
}
df.rename(rename_cols_map, axis=1, inplace=True)
# add drop column to logs:
for col in drop_cols_list:
rename_cols_map.update({col: "_DROPPED_"})
# log the op
tp = os.path.join(models_dest, "preproc-column_map.json")
context.log_artifact("preproc-column_map.json",
body=json.dumps(rename_cols_map),
local_path=tp)
# VALUE transformations
# clean
# truncate reply to "No"
df = df.applymap(lambda x: "No" if str(x).startswith("No ") else x)
# encode numerical type as category bins (ordinal)
bins = [0, 12, 24, 36, 48, 60, np.inf]
labels = [0, 1, 2, 3, 4, 5]
df["tenure_map"] = pd.cut(df.tenure, bins, labels=False)
tenure_map = dict(zip(bins, labels))
# save this transformation
tp = os.path.join(models_dest, "preproc-numcat_map.json")
context.log_artifact(
"preproc-numcat_map.json",
body=bytes(json.dumps(tenure_map).encode("utf-8")),
local_path=tp,
)
context.log_dataset(cleaned_key, df=df, format=file_ext, index=False)
# label encoding - generate model for each column saved in dict
# some of these columns may be hot encoded in the training step
fix_cols = [
"gender",
"partner",
"deps",
"OnlineSecurity",
"OnlineBackup",
"DeviceProtection",
"TechSupport",
"StreamingTV",
"StreamingMovies",
"PhoneService",
"MultipleLines",
"PaperlessBilling",
"InternetService",
"Contract",
"PaymentMethod",
"labels",
]
d = defaultdict(LabelEncoder)
df[fix_cols] = df[fix_cols].apply(
lambda x: d[x.name].fit_transform(x.astype(str)))
context.log_dataset(encoded_key, df=df, format=file_ext, index=False)
model_bin = dumps(d)
context.log_model(
"model",
body=model_bin,
artifact_path=os.path.join(context.artifact_path, models_dest),
model_file="model.pkl",
)
def arc_to_parquet(context: MLClientCtx,
archive_url: DataItem,
header: List[str] = [None],
chunksize: int = 0,
dtype=None,
encoding: str = "latin-1",
key: str = "data",
dataset: str = "None",
part_cols=[],
file_ext: str = "parquet",
index: bool = False,
refresh_data: bool = False,
stats: bool = False) -> None:
"""Open a file/object archive and save as a parquet file or dataset
Notes
-----
* this function is typically for large files, please be sure to check all settings
* partitioning requires precise specification of column types.
* the archive_url can be any file readable by pandas read_csv, which includes tar files
* if the `dataset` parameter is not empty, then a partitioned dataset will be created
instead of a single file in the folder `dataset`
* if a key exists already then it will not be re-acquired unless the `refresh_data` param
is set to `True`. This is in case the original file is corrupt, or a refresh is
required.
:param context: the function context
:param archive_url: MLRun data input (DataItem object)
:param chunksize: (0) when > 0, row size (chunk) to retrieve
per iteration
:param dtype destination data type of specified columns
:param encoding ("latin-8") file encoding
:param key: key in artifact store (when log_data=True)
:param dataset: (None) if not None then "target_path/dataset"
is folder for partitioned files
:param part_cols: ([]) list of partitioning columns
:param file_ext: (parquet) csv/parquet file extension
:param index: (False) pandas save index option
:param refresh_data: (False) overwrite existing data at that location
:param stats: (None) calculate table stats when logging artifact
"""
base_path = context.artifact_path
os.makedirs(base_path, exist_ok=True)
archive_url = archive_url.local()
if dataset is not None:
dest_path = os.path.join(base_path, dataset)
exists = os.path.isdir(dest_path)
else:
dest_path = os.path.join(base_path, key + f".{file_ext}")
exists = os.path.isfile(dest_path)
if not exists:
context.logger.info("destination file does not exist, downloading")
if chunksize > 0:
header = _chunk_readwrite(archive_url, dest_path, chunksize,
encoding, dtype, dataset)
context.log_dataset(key=key,
stats=stats,
format='parquet',
target_path=dest_path)
else:
df = pd.read_csv(archive_url)
context.log_dataset(key, df=df, format=file_ext, index=index)
else:
context.logger.info("destination file already exists, nothing done")
