def __enter__(self):
"""Download files for datastore.
:return:
"""
module_logger.debug("Enter __enter__ function of datastore cmgr")
from azureml.core import Datastore, Dataset
for key, value in self._config.items():
df_config, _ = self._to_data_reference_config(value)
if self._is_upload(df_config):
if df_config.path_on_compute:
dir_to_create = os.path.normpath(
os.path.dirname(df_config.path_on_compute))
if dir_to_create:
_safe_mkdirs(dir_to_create)
else:
target_path = df_config.data_store_name
if df_config.path_on_compute:
target_path = os.path.join(df_config.data_store_name,
df_config.path_on_compute)
# The target_path is always set using the data store name with no way
# for the user to overwrite this behavior. The user might attempt to use ../ in
# the path on compute as a solution but this throws an exception
# because the path is not normalized.
# Normalizing the path to allow the user to use up-level references.
target_path = os.path.normpath(target_path)
if self._is_download(df_config):
self._validate_config(df_config, key)
ds = Datastore(workspace=self._workspace,
name=df_config.data_store_name)
if self._is_datastore_adlsgen1(ds):
_log_and_print(
"AzureDataLake Gen1 used as Datastore for download"
)
if df_config.path_on_data_store is None:
df_config.path_on_data_store = ""
Dataset.File.from_files(
(ds, df_config.path_on_data_store)).download(
os.path.join(target_path,
df_config.path_on_data_store),
overwrite=df_config.overwrite)
else:
count = ds.download(
target_path=target_path,
prefix=df_config.path_on_data_store,
overwrite=df_config.overwrite)
if count == 0:
import warnings
warnings.warn(
"Downloaded 0 files from datastore {} with path {}."
.format(ds.name, df_config.path_on_data_store))
else:
_safe_mkdirs(target_path)
module_logger.debug("Exit __enter__ function of datastore cmgr")
#%% List all blobstores
for store in ws.datastores:
print(store)
#%% connect to a datastore by name
blob_store = Datastore(ws, "workspaceblobstore")
print("\n" + f"Connected to blobstore: {blob_store.name}")
#%%
# ** Downloading training data from the Blobstore **
#%% download the file from the blobstore to your local machine (or compute instance)
blob_path = "Campus_Recruitment/Raw_Data"# if None will download whole blob
local_path = "./"
blob_store.download(target_path=local_path,
prefix=blob_path,
overwrite=True,
show_progress=True)
#%% Load the data into memory
df = pd.read_csv("./Campus_Recruitment/Raw_Data/datasets_596958_1073629_Placement_Data_Full_Class.csv")
df[:10]
#%%
# ** Transform the data for use with our model **
#%% transform some column values into numeric and categorical
df['male'] = df['gender'].map({'M':1, 'F':0})
df['education_board_is_central'] = df['ssc_b'].map({'Central':1, 'Others':0})
df['hsc_s'] = df['hsc_s'].map({'Commerce':0 , 'Science':1 , 'Arts':2})
df['workex_bool'] = df['workex'].map({'Yes':1, 'No':0})
#%% drops nan values in columns we are using for the pca
