Open
Description
MLRun Version checks
-
I have checked that this issue has not already been reported.
-
I have confirmed this bug exists on the latest version of MLRun CE.
Reproducible Example
import oracledb
import pandas as pd
username = "C##xxx"
password = "xxx"
host = "192.168.1.6"
port = "1521"
service_name = "xe"
conn = oracledb.connect(user=username, password=password, host=host, port=port, service_name=service_name)
# Create a cursor
cursor = conn.cursor()
# Define the SQL statement for selecting data
select_sql = "SELECT * FROM NPRA_IMPORT"
# Execute the SQL statement to fetch data
cursor.execute(select_sql)
# Fetch all rows of data
rows = cursor.fetchall()
# Define the SQL statement to fetch column names for a table
table_name = 'NPRA_IMPORT'
select_sql2 = f"SELECT column_name FROM all_tab_columns WHERE table_name = '{table_name}'"
# Execute the SQL statement to fetch data
cursor.execute(select_sql2)
# Fetch all rows of data
columns = cursor.fetchall()
# Define column names
column_names = [column[0].lower() for column in columns]
# Create a DataFrame from the fetched rows with column names
df = pd.DataFrame(rows, columns=column_names)
%%writefile data-prep-oracle-db.py
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.feature_selection import SelectKBest, f_classif
import oracledb
import mlrun
def get_oracle_data():
# Connection details
username = "C##xxx"
password = "xxx"
host = "192.168.1.6"
port = "1521"
service_name = "xe"
conn = oracledb.connect(user=username, password=password, host=host, port=port, service_name=service_name)
# Create a cursor
cursor = conn.cursor()
# Define the SQL statement for selecting data
select_sql = "SELECT * FROM NPRA_IMPORT"
# Execute the SQL statement to fetch data
cursor.execute(select_sql)
# Fetch all rows of data
rows = cursor.fetchall()
# Define the SQL statement to fetch column names for a table
table_name = 'NPRA_IMPORT'
select_sql2 = f"SELECT column_name FROM all_tab_columns WHERE table_name = '{table_name}'"
# Execute the SQL statement to fetch data
cursor.execute(select_sql2)
# Fetch all rows of data
columns = cursor.fetchall()
# Define column names
column_names = [column[0].lower() for column in columns]
# Create a DataFrame from the fetched rows with column names
df = pd.DataFrame(rows, columns=column_names)
return df
def load_data(df):
df.drop("customer_id", axis=1, inplace=True)
df.drop_duplicates(inplace=True)
df.dropna(axis=0, inplace=True)
return df
def remove_outliers_iqr(df, col):
Q1 = df[col].quantile(0.25)
Q3 = df[col].quantile(0.75)
IQR = Q3 - Q1
lower_bound = Q1 - 1.5 * IQR
upper_bound = Q3 + 1.5 * IQR
df = df[(df[col] >= lower_bound)]
df = df[(df[col] <= upper_bound)]
return df
def label_encode_categorical_columns(df):
le = LabelEncoder()
for col in df.select_dtypes(include='object'):
df[col] = le.fit_transform(df[col])
return df
def preprocess_data(data):
can_have_outlier = ["person_age","person_income","person_emp_length","cb_person_cred_hist_length","loan_amnt"]
for col in can_have_outlier:
data = remove_outliers_iqr(data, col)
preprocessed_data = label_encode_categorical_columns(data)
return preprocessed_data
def data_balance(new_df):
# Divide by class
df_class_0 = new_df[new_df['loan_status'] == 0]
df_class_1 = new_df[new_df['loan_status'] == 1]
count_class_0, count_class_1 = new_df['loan_status'].value_counts()
# random over sampling
df_class_1_over = df_class_1.sample(count_class_0, replace=True)
new_df = pd.concat([df_class_0, df_class_1_over], axis=0)
return new_df
@mlrun.handler(outputs=["dataset", "label_column"])
def credit_risk_dataset_generator():
"""
A function which generates the credit risk dataset
"""
dataset = get_oracle_data()
data = load_data(dataset)
preprocessed_data = preprocess_data(data)
for_model_df = data_balance(preprocessed_data)
return for_model_df, "loan_status"Issue Description
I am trying to fetch data from Oracle database and trying to fed it to mlrun architecture. I'm able to access database locally, but getting this error when trying to ingest it in pipeline.
Expected Behavior
I should be able to ingest data into pipeline from oracle database.
Installation OS
Windows
Installation Method
Kubernetes
Python Version
3.9.13
MLRun Version
Mlrun CE 0.6.2
Additional Information
I'm Using docker Desktop to work with Kubernetes Clusture.
Docker Version- v4.9.1
Kubectl version - v1.24
Helm version - v3.11.3
Dataset using - "credit risk dataset"
Metadata
Metadata
Assignees
Labels
No labels