___

Text Classification Assessment¶

Goal: Given a set of text movie reviews that have been labeled negative or positive¶

For more information on this dataset visit http://ai.stanford.edu/~amaas/data/sentiment/

Complete the tasks in bold below!¶

Task: Perform imports and load the dataset into a pandas DataFrame For this exercise you can load the dataset from '../DATA/moviereviews.csv'.

In [1]:

# CODE HERE

In [2]:

import numpy as np
import pandas as pd

In [3]:

df = pd.read_csv('../DATA/moviereviews.csv')

In [4]:

df.head()

Out[4]:

	label	review
0	neg	how do films like mouse hunt get into theatres...
1	neg	some talented actresses are blessed with a dem...
2	pos	this has been an extraordinary year for austra...
3	pos	according to hollywood movies made in last few...
4	neg	my first press screening of 1998 and already i...

TASK: Check to see if there are any missing values in the dataframe.

In [7]:

#CODE HERE

In [8]:

Out[8]:

label      0
review    35
dtype: int64

TASK: Remove any reviews that are NaN

In [10]:

TASK: Check to see if any reviews are blank strings and not just NaN. Note: This means a review text could just be: "" or " " or some other larger blank string. How would you check for this? Note: There are many ways! Once you've discovered the reviews that are blank strings, go ahead and remove them as well. Click me for a big hint

In [ ]:

In [18]:

Out[18]:

In [19]:

Out[19]:

	label	review
57	neg
71	pos
147	pos
151	pos
283	pos
307	pos
313	neg
323	pos
343	pos
351	neg
427	pos
501	neg
633	pos
675	neg
815	neg
851	neg
977	neg
1079	neg
1299	pos
1455	neg
1493	pos
1525	neg
1531	neg
1763	neg
1851	neg
1905	pos
1993	pos

In [21]:

In [22]:

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1938 entries, 0 to 1999
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   label   1938 non-null   object
 1   review  1938 non-null   object
dtypes: object(2)
memory usage: 45.4+ KB

TASK: Confirm the value counts per label:

In [23]:

#CODE HERE

In [24]:

Out[24]:

pos    969
neg    969
Name: label, dtype: int64

EDA on Bag of Words¶

Bonus Task: Can you figure out how to use a CountVectorizer model to get the top 20 words (that are not english stop words) per label type? Note, this is a bonus task as we did not show this in the lectures. But a quick cursory Google search should put you on the right path. Click me for a big hint

In [45]:

#CODE HERE

In [46]:

In [55]:

Top 20 words used for Negative reviews.
[('film', 4063), ('movie', 3131), ('like', 1808), ('just', 1480), ('time', 1127), ('good', 1117), ('bad', 997), ('character', 926), ('story', 908), ('plot', 888), ('characters', 838), ('make', 813), ('really', 743), ('way', 734), ('little', 696), ('don', 683), ('does', 666), ('doesn', 648), ('action', 635), ('scene', 634)]

In [56]:

Top 20 words used for Positive reviews.
[('film', 5002), ('movie', 2389), ('like', 1721), ('just', 1273), ('story', 1199), ('good', 1193), ('time', 1175), ('character', 1037), ('life', 1032), ('characters', 957), ('way', 864), ('films', 851), ('does', 828), ('best', 788), ('people', 769), ('make', 764), ('little', 751), ('really', 731), ('man', 728), ('new', 702)]

Training and Data¶

TASK: Split the data into features and a label (X and y) and then preform a train/test split. You may use whatever settings you like. To compare your results to the solution notebook, use test_size=0.20, random_state=101

In [ ]:

#CODE HERE

In [57]:

Training a Mode¶

TASK: Create a PipeLine that will both create a TF-IDF Vector out of the raw text data and fit a supervised learning model of your choice. Then fit that pipeline on the training data.

In [ ]:

#CODE HERE

In [74]:

In [76]:

Out[76]:

Pipeline(steps=[('tfidf', TfidfVectorizer()), ('svc', LinearSVC())])

TASK: Create a classification report and plot a confusion matrix based on the results of your PipeLine.

In [77]:

#CODE HERE

In [78]:

In [79]:

In [80]:

              precision    recall  f1-score   support

         neg       0.81      0.86      0.83       191
         pos       0.85      0.81      0.83       197

    accuracy                           0.83       388
   macro avg       0.83      0.83      0.83       388
weighted avg       0.83      0.83      0.83       388

In [81]:

Out[81]:

<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x1f370d0b790>

27 KiB

Raw Blame History

Text Classification Assessment¶

Goal: Given a set of text movie reviews that have been labeled negative or positive¶

Complete the tasks in bold below!¶

EDA on Bag of Words¶

Training and Data¶

Training a Mode¶

Great job!¶

27 KiB Raw Blame History

Text Classification Assessment¶

Goal: Given a set of text movie reviews that have been labeled negative or positive¶

Complete the tasks in bold below!¶

EDA on Bag of Words¶

Training and Data¶

Training a Mode¶

Great job!¶

27 KiB

Raw Blame History