jinhangjiang

gpu_info = !nvidia-smi
gpu_info = '\n'.join(gpu_info)
if gpu_info.find('failed') >= 0:
  print('Not connected to a GPU')
else:
  print(gpu_info)

jinhangjiang

df['Boilerplate'] = mts.Boilerplate(sent_tok, n = 4, min_doc = 5, get_ngram = False)

jinhangjiang

from ._Class1 import Function1
from ._Class1 import Function2
from ._Class2 import Function1
... 

jinhangjiang

# Call Model
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels = num_labels).to("cuda")

jinhangjiang

##### AVERAGE
average_pred = (XGB_pred+
                KNN_pred+
                MLPC_pred+
                RandomForest_pred+
                DecisionTree_pred)/5

#make submission table
FiveModelAveragePrediction = pd.DataFrame(
  {'QuoteNumber':df, 

jinhangjiang

##### Decision Tree
DecisionTree = DecisionTreeClassifier()
DecisionTree.fit(data, label)
DecisionTree_pred = DecisionTree.predict(Test)
#make submission table
DecisionTreePrediction = pd.DataFrame(
  {'QuoteNumber':df, 
   'QuoteConversion_Flag':DecisionTree_pred})
#save file
DecisionTreePrediction.to_csv('DecisionTree1.csv', 

jinhangjiang

#load libraries
import pandas as pd
import numpy as np
#from statistics import *
import os
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from xgboost import XGBClassifier

jinhangjiang

#set parameters
params = {'voting':['hard', 'soft'],
          'weights':[(1,1,1,1,1), (2,1,1,1,1), 
                     (1,2,1,1,1), (1,1,2,1,1),
                     (1,1,1,2,1), (1,1,1,1,2), 
                     (1,1,1,2,2), (2,1,1,1,2)]}

#fit gridsearch & print best params
grid = GridSearchCV(vc, params)
grid.fit(X, y)

jinhangjiang

#load packages
from sklearn.ensemble import VotingClassifier
from sklearn.model_selection import cross_val_score, GridSearchCV

#fit a base model
vc = VotingClassifier([('dt', DecisionTree), 
                       ('KNN', KNN), 
                       ('MLPC', MLPC), 
                       ('rf', RandomForest), 
                       ('xgb', XGB)])

jinhangjiang

def ThreeDplot(model):
    
    "Creates TSNE model and plots it"
    "Get the labels and vectors from ndoe2vec mode"
    labels = []
    tokens = []

    for word in model.wv.vocab:
        tokens.append(model[word])
        labels.append(word)