sudarshan-koirala

# Disclamer: This code is not written by me. Its taken from https://github.com/imartinez/privateGPT/pull/91. 
# All credit goes to `vnk8071` as I mentioned in the video.
# As this code was still in the pull request while I was creating the video, did some modifications so that it works for me locally.

import gradio as gr
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.chains import RetrievalQA
from langchain.embeddings import LlamaCppEmbeddings
from langchain.llms import GPT4All, LlamaCpp
from langchain.vectorstores import Chroma

marketneutral

def make_tooltipped_df(df, tooltips: dict):
  """
  import pandas as pd
  from IPython.display import display, HTML

  # Sample DataFrame
  data = {'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]}
  df = pd.DataFrame(data)

  # Apply styles to the DataFrame

ih2502mk

Lecture 1: Introduction to Research — [📝Lecture Notebooks] [▶️Video]
Lecture 2: Introduction to Python — [📝Lecture Notebooks] [▶️Video]
Lecture 3: Introduction to NumPy — [📝Lecture Notebooks] [▶️Video]
Lecture 4: Introduction to pandas — [📝Lecture Notebooks] [▶️Video]
Lecture 5: Plotting Data — [📝Lecture Notebooks] [[▶️Vide

marketneutral

from joblib import Parallel, delayed

def expesive_calc(df):
    df['new_col'] = ...
    return df

def apply_parallel(gdf, func):
    ret_list = Parallel(n_jobs=8)(delayed(func)(group) for name, group in gdf)
    return pd.concat(ret_list)

p3jitnath

# WARNING : This gist in the current form is a collection of command examples. Please exercise caution where mentioned.

# Docker
sudo apt-get update
sudo apt-get remove docker docker-engine docker.io
sudo apt install docker.io
sudo systemctl start docker
sudo systemctl enable docker
docker --version

ledell

### Kaggle Days SF: Hackathon submission (8th place) 

# I used the latest version of H2O (3.24.0.1)
# Latest stable always here: http://h2o-release.s3.amazonaws.com/h2o/latest_stable.html
# H2O 3.24.0.1: http://h2o-release.s3.amazonaws.com/h2o/rel-yates/1/index.html
# If you are a Python user, you can use the demo Python code available on the H2O AutoML User Guide 
# instead: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html

# Unfortunately it was a private competition, so the data is not publicly available! 

twiecki

import dask
import dask.array as da
import dask.dataframe as dd
import sparse

@dask.delayed(pure=True)
def corr_on_chunked(chunk1, chunk2, corr_thresh=0.9):
    return sparse.COO.from_numpy((np.dot(chunk1, chunk2.T) > corr_thresh))
        
def chunked_corr_sparse_dask(data, chunksize=5000, corr_thresh=0.9):

HarshTrivedi

import torch
from torch import LongTensor
from torch.nn import Embedding, LSTM
from torch.autograd import Variable
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
#
#     Step 1: Construct Vocabulary
#     Step 2: Load indexed data (list of instances, where each instance is list of character indices)

wiso

import numpy as np

def correlation_from_covariance(covariance):
    v = np.sqrt(np.diag(covariance))
    outer_v = np.outer(v, v)
    correlation = covariance / outer_v
    correlation[covariance == 0] = 0
    return correlation

logandillard

import math
import numpy as np
from sklearn.linear_model import Ridge


class LinearModelTree:
    def __init__(self, min_node_size, node_model_fit_func, min_split_improvement=0):
        self.min_node_size = min_node_size
        self.node_model_fit_func = node_model_fit_func
        self.min_split_improvement = min_split_improvement