alexcpn

Data for this

https://www.kaggle.com/datasets/alexpunnen/wikipedia-history-of-save-failures

Running in Docker Container

docker run --rm -it --net=host -v /home/xxx:/home alexcpn/fb_prophet_python:1 cd /home/xx//python python outlier_full.py

alexcpn

Note: Region of Bucket and Data should be same

BigQuery ML Model - CREATE or REPLACE MODEL

CREATE OR REPLACE MODEL `computervision-159307.test.logistic_model` OPTIONS(model_type='LOGISTIC_REG',
    input_label_cols=['output']) AS
SELECT
  age,
 cp,

alexcpn

def softmax(x):
    """Compute softmax values for each sets of scores in x.
    why the max - see Eli's post https://eli.thegreenplace.net/2016/the-softmax-function-and-its-derivative/
    """
    e_x = np.exp(x - np.max(x)) # 
    return e_x / e_x.sum()
  
def derv_softmax(s): # where x is the input
    """

alexcpn

#!/bin/bash

KUBELET_HOME=/var/lib

for podid in 05156637-1f26-4437-a0ea-3b60062c454a;
do
    if [ ! -d ${KUBELET_HOME}/kubelet/pods/$podid ]; then
        break
    fi

alexcpn

    def conv2d(self, image, filter):
        imagesize = image.shape
        filter_size = filter.shape
        print(imagesize)
        i = imagesize[0]
        j = imagesize[1]
        k = imagesize[2]
        fl = filter_size[0]  # filter length of row
        print("Image=", i, j, k, "Filter=", fl)
        di = -1

alexcpn

Please follow the steps as is for correct installation

Step 1: Install Rook

We are taking from version v1.5.10. The latest v1.6.1 has a bug for external Ceph (git clone --single-branch --branch v1.5.10 https://github.com/rook/rook.git)

kubectl create -f rookv1.5.10/operator/crds.yaml

alexcpn

Running systemd inside a Container

Some context here - https://developers.redhat.com/blog/2019/04/24/how-to-run-systemd-in-a-container

With Docker you need to mount the host volume -v /sys/fs/cgroup:/sys/fs/cgroup:ro However this is not needed for podman

If Kubernetes cluster is still using Docker, this will not work in pod wihtout these mounts; but if using Containerd directly (kubelet--> Containerd-->runc) I am not sure

alexcpn

# https://www.kubeflow.org/docs/components/pipelines/sdk/pipelines-metrics/ - v1 flow
def model_evaluvate_v1(modelpath:InputPath("TF_Model"),
                   test_dataset_path:InputPath("TF_DataSet"))  -> NamedTuple("Outputs", [ ("mlpipeline_metrics", "Metrics"),]):
    from tensorflow import keras
    import tensorflow as tf
    from sklearn.metrics import confusion_matrix
    import json
    
    # Load data from the file path /KF components
    model = keras.models.load_model(modelpath)

alexcpn

  vop = dsl.VolumeOp(
        name="create-pvc",
        resource_name="my-pvc",
        modes=dsl.VOLUME_MODE_RWO,
        size='1Gi')  
  # Passes a pipeline parameter and a constant value to the `add_op` factory
  # function.
  first_task = kubeflow_task(a).add_pvolumes({"/mnt": vop.volume})
  
----

alexcpn

read_data = create_component_from_func(readdata,base_image="tensorflow/tensorflow:2.6.0", \
                                       packages_to_install=["pandas==0.24","sklearn","numpy","pyarrow"],\
                                       output_component_file='read_data_component.yaml')
# OR
read_data = load_component_from_url("https://gist.github.com/alexcpn/f82d63976656ffda0a508f9bafa28440/raw/628b828e13825e58f6ddfdf0bf0471e2ff93d527/read_data_component.yaml")

process_data = create_component_from_func(process_data,base_image="tensorflow/tensorflow:2.6.0", packages_to_install=["pandas==0.24","sklearn","numpy","pyarrow"])

create_nn_model = create_component_from_func(create_nn_model,base_image="tensorflow/tensorflow:2.5.1")
train_model = create_component_from_func(train_model,base_image="tensorflow/tensorflow:2.5.1")