korkridake

# -*- coding: utf-8 -*-
"""DS Agent - Walmart Stocks Data 2025 (Unfiltered).ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1xQPflL75hlDCGRRntyEBdSt_DgegxlTi

# Task
Hey Data Science Agent, can you help with the data analysis on this dataset? It includes EDA, descriptive stats, and some data visualizations. If you can, could you also suggest some time-series modeling?

korkridake

korkridake

import numpy as np
import matplotlib.pyplot as plt
import azureml.core
# Display the core SDK version number
print("Azure ML SDK Version: ", azureml.core.VERSION)

# Define an environment
from azureml.core.environment import Environment
from azureml.core.conda_dependencies import CondaDependencies

korkridake

import numpy as np
import matplotlib.pyplot as plt
import azureml.core
# Display the core SDK version number
print("Azure ML SDK Version: ", azureml.core.VERSION)

# Define an environment
from azureml.core.environment import Environment
from azureml.core.conda_dependencies import CondaDependencies

korkridake

%%writefile score.py
import json
import numpy as np
import os
import pickle
import joblib

def init():
    global model
    ##################################################################################################

korkridake

# Import libraries
import json
import numpy as np
from azureml.core.model import Model
import joblib

# Load model
model_path = Model.get_model_path(model_name="sklearn_regression_model.pkl")
model = joblib.load(model_path)

korkridake

# Get hold of the current run
run = Run.get_context()

# Experiment parameters
args = {
    "n_estimators": 120
}

reg_model = RandomForestRegressor(**args)
reg_model.fit(data["train"]["X"], data["train"]["y"])

korkridake

# Load data in  Pandas
df = dataset.to_pandas_dataframe()
print(df.shape)
df.head()

# Preprocess data
df = df.drop_duplicates()
df = df.drop(["dateCrawled","dateCreated","lastSeen", "seller", "name", "postalCode"] , axis = 1)
df["notRepairedDamage"] = df["notRepairedDamage"].fillna("nein")
df["fuelType"] = df["fuelType"].fillna("benzin")

korkridake

# Install H2O packages
if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }
pkgs <- c("RCurl","jsonlite")
for (pkg in pkgs) {
  if (! (pkg %in% rownames(installed.packages()))) { install.packages(pkg) }
}
install.packages("h2o", type="source", repos=(c("http://h2o-release.s3.amazonaws.com/h2o/latest_stable_R")))
library(h2o)
localH2O = h2o.init()

korkridake

# Get the datastore to upload prepared data
datastore = ws.get_default_datastore()

# Upload the local file from src_dir to the target_path in datastore
datastore.upload(src_dir='../aml-kaggle/datasets/', target_path='ds_regression')

# Create a dataset referencing the cloud location
dataset = Dataset.Tabular.from_delimited_files(datastore.path('ds_regression/autos.csv'))

# Register a dataset