I currently have following script that helps to find the best model for a doc2vec model. It works like this: First train a few models based on given parameters and then test against a classifier. Finally, it outputs the best model and classifier (I hope).
Data
Example data (data.csv) can be downloaded here: https://pastebin.com/takYp6T8 Note that the data has a structure that should make an ideal classifier with 1.0 accuracy.
Script
import sys
import os
from time import time
from operator import itemgetter
import pickle
import pandas as pd
import numpy as np
from argparse import ArgumentParser
from gensim.models.doc2vec import Doc2Vec
from gensim.models import Doc2Vec
import gensim.models.doc2vec
from gensim.models import KeyedVectors
from gensim.models.doc2vec import TaggedDocument, Doc2Vec
from sklearn.base import BaseEstimator
from gensim import corpora
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
dataset = pd.read_csv("data.csv")
class Doc2VecModel(BaseEstimator):
def __init__(self, dm=1, size=1, window=1):
self.d2v_model = None
self.size = size
self.window = window
self.dm = dm
def fit(self, raw_documents, y=None):
# Initialize model
self.d2v_model = Doc2Vec(size=self.size, window=self.window, dm=self.dm, iter=5, alpha=0.025, min_alpha=0.001)
# Tag docs
tagged_documents = []
for index, row in raw_documents.iteritems():
tag = '{}_{}'.format("type", index)
tokens = row.split()
tagged_documents.append(TaggedDocument(words=tokens, tags=[tag]))
# Build vocabulary
self.d2v_model.build_vocab(tagged_documents)
# Train model
self.d2v_model.train(tagged_documents, total_examples=len(tagged_documents), epochs=self.d2v_model.iter)
return self
def transform(self, raw_documents):
X = []
for index, row in raw_documents.iteritems():
X.append(self.d2v_model.infer_vector(row))
X = pd.DataFrame(X, index=raw_documents.index)
return X
def fit_transform(self, raw_documents, y=None):
self.fit(raw_documents)
return self.transform(raw_documents)
param_grid = {'doc2vec__window': [2, 3],
'doc2vec__dm': [0,1],
'doc2vec__size': [100,200],
'logreg__C': [0.1, 1],
}
pipe_log = Pipeline([('doc2vec', Doc2VecModel()), ('log', LogisticRegression())])
log_grid = GridSearchCV(pipe_log,
param_grid=param_grid,
scoring="accuracy",
verbose=3,
n_jobs=1)
fitted = log_grid.fit(dataset["posts"], dataset["type"])
# Best parameters
print("Best Parameters: {}\n".format(log_grid.best_params_))
print("Best accuracy: {}\n".format(log_grid.best_score_))
print("Finished.")
I do have following questions regarding my script (I combine them here to avoid three posts with the same code snippet):
- What's the purpose of
def __init__(self, dm=1, size=1, window=1):? Can I possibly remove this part, somehow (tried unsuccessfully)? - How can I add a
RandomForestclassifier (or others) to the GridSearch workflow/pipeline? - How could a train/test data split added to the code above, as the current script only trains on the full dataset?
