Skip to content

rishabhmonga119/Customer_Lead_Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The given case study was to analyse the file CustomerData_LeadGenerator.csv, identify training data and labels within the dataset, and train and deploy a machine learning model. On closely examining the data, I chose to use b_gekauft_gesamt as my target label and the other features (except the feature fakeID) as the training data.

Prerequistes to start the MLFlow server:

  1. Download and install conda (https://docs.conda.io/en/latest/miniconda.html)

Steps to start the prediction server and make predictions:

  1. Run command:
conda env create --file conda.yaml
  1. Activate conda environment:
conda activate RandomForest
  1. Run command to start the prediction server:
mlflow models serve -m mlruns/0/8ad24d33836340df9a724d04ef972154/artifacts/model -p 1234
  1. Add the batch data in the batch_data.csv file within the data folder. It should contain all the columns as in CustomerData_LeadGenerator.csv, except the target label b_gekauft_gesamt and the column fakeID. If no data is given in batch_data.csv file, the last 10 rows of the test dataset is used as a batch to make predictions.

  2. For the batch scoring, add the true labels for the batch in batch_true_labels.txt as a list.

  3. Run the shell script make_predictions.sh to make predictions and evaluate model performance

sh make_predictions.sh

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published