lgray

(py36) [lagray@fermicloud318 laurelin]$ python ../test_laurelin.py
SLF4J: Class path contains multiple SLF4J bindings.
SLF4J: Found binding in [jar:file:/opt/spark-2.4.3-bin-hadoop2.7/jars/slf4j-log4j12-1.7.16.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: Found binding in [jar:file:/opt/hadoop-2.7.2/share/hadoop/common/lib/slf4j-log4j12-1.7.10.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.
SLF4J: Actual binding is of type [org.slf4j.impl.Log4jLoggerFactory]
Ivy Default Cache set to: /home/lagray/.ivy2/cache
The jars for the packages stored in: /home/lagray/.ivy2/jars
:: loading settings :: url = jar:file:/opt/spark-2.4.3-bin-hadoop2.7/jars/ivy-2.4.0.jar!/org/apache/ivy/core/settings/ivysettings.xml
edu.vanderbilt.accre#laurelin added as a dependency

lgray

import fast_curator
import fast_flow.v1 as fast_flow
import pprint
import copy

datasets = fast_curator.read.from_yaml('curator/file_list.yml')

pprint.pprint(datasets)

coffea_datasets = {}

lgray

lgray

lgray

import pyarrow as pa
import pyarrow.parquet as pq

def nanoaod2arrowtable(params):
    """
    takes as input a (list of) root file(s) of ~flat ntuples
    and convert into a single arrow table
    """
    
    random.seed(None)

lgray

# here's a dynamic reduction network that can categorize
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.drn = DynamicReductionNetwork(input_dim=3, hidden_dim=64,
                                           k = 16,
                                           output_dim=2, aggr='add',
                                           norm=torch.tensor([1., 1./27., 1./27.]))
        
    def forward(self, data):

lgray

import torch
import torch.nn.functional as F
import torch_geometric.transforms as T
import torch.nn as nn
from torch_geometric.nn import EdgeConv, DynamicEdgeConv

#let's try a basic implementation of really simple message passing
from torch_scatter import scatter_add
class NodeNetwork(nn.Module):
    def __init__(self, input_dim, output_dim, hidden_activation=nn.Tanh):

lgray

import os
import os.path as osp
import math

import numpy as np
import torch
import gc
import torch.nn as nn
import torch.nn.functional as F
import torch_geometric.transforms as T

lgray

Traceback (most recent call last):
  File "mnist_nn_conv.py", line 71, in <module>
    model = Net().to(device)
  File "mnist_nn_conv.py", line 45, in __init__
    self.conv1 = conv1.jittable(x=init_data.x, edge_index=init_data.edge_index, edge_attr=init_data.edge_attr)
  File "/Users/lagray/pytorch_work/pytorch_geometric/torch_geometric/nn/conv/message_passing.py", line 608, in jittable
    out = torch.jit.script(out)
  File "/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/__init__.py", line 1261, in script
    return torch.jit._recursive.create_script_module(obj, torch.jit._recursive.infer_methods_to_compile)
  File "/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 305, in create_script_module

lgray

import sys
import os
import requests
import argparse
import json
from uuid import uuid1
import pprint

os.environ['NODE_TLS_REJECT_UNAUTHORIZED'] = '0'