From a7bd62ad739e2ff2212be05a3a05fedccbcbd72e Mon Sep 17 00:00:00 2001
From: noahcostello5 <noahcostello5@gmail.com>
Date: Tue, 26 Feb 2019 19:45:14 -0600
Subject: [PATCH] Added method functionality to Review Class.
---
.vscode/launch.json | 70 ++++++++++++++++++++
.vscode/settings.json | 3 +
sentiment.py | 148 +++++++++++++++++++++++++++++++++++-------
3 files changed, 196 insertions(+), 25 deletions(-)
create mode 100644 .vscode/launch.json
create mode 100644 .vscode/settings.json
diff --git a/.vscode/launch.json b/.vscode/launch.json
new file mode 100644
index 0000000..92a2fa2
--- /dev/null
+++ b/.vscode/launch.json
@@ -0,0 +1,70 @@
+{
+ // Use IntelliSense to learn about possible attributes.
+ // Hover to view descriptions of existing attributes.
+ // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+ "version": "0.2.0",
+ "configurations": [
+ {
+ "name": "Python: Current File (Integrated Terminal)",
+ "type": "python",
+ "request": "launch",
+ "program": "${file}",
+ "console": "integratedTerminal"
+ },
+ {
+ "name": "Python: Remote Attach",
+ "type": "python",
+ "request": "attach",
+ "port": 5678,
+ "host": "localhost",
+ "pathMappings": [
+ {
+ "localRoot": "${workspaceFolder}",
+ "remoteRoot": "."
+ }
+ ]
+ },
+ {
+ "name": "Python: Module",
+ "type": "python",
+ "request": "launch",
+ "module": "enter-your-module-name-here",
+ "console": "integratedTerminal"
+ },
+ {
+ "name": "Python: Django",
+ "type": "python",
+ "request": "launch",
+ "program": "${workspaceFolder}/manage.py",
+ "console": "integratedTerminal",
+ "args": [
+ "runserver",
+ "--noreload",
+ "--nothreading"
+ ],
+ "django": true
+ },
+ {
+ "name": "Python: Flask",
+ "type": "python",
+ "request": "launch",
+ "module": "flask",
+ "env": {
+ "FLASK_APP": "app.py"
+ },
+ "args": [
+ "run",
+ "--no-debugger",
+ "--no-reload"
+ ],
+ "jinja": true
+ },
+ {
+ "name": "Python: Current File (External Terminal)",
+ "type": "python",
+ "request": "launch",
+ "program": "${file}",
+ "console": "externalTerminal"
+ }
+ ]
+}
\ No newline at end of file
diff --git a/.vscode/settings.json b/.vscode/settings.json
new file mode 100644
index 0000000..26fff8e
--- /dev/null
+++ b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+ "python.pythonPath": "C:\\Users\\noahc\\AppData\\Local\\Programs\\Python\\Python37\\python.exe"
+}
\ No newline at end of file
diff --git a/sentiment.py b/sentiment.py
index 71e8bd9..48a568b 100644
--- a/sentiment.py
+++ b/sentiment.py
@@ -1,6 +1,7 @@
-from enum import Enum
+from enum import Enum, auto
import math
+
class MenuOption(Enum):
SHOW_REVIEWS = 'Show reviews'
CHECK_TOKEN = 'Check if a token is present'
@@ -11,60 +12,143 @@ class MenuOption(Enum):
SHOW_ADJUSTED_SENTENCE_STATISTICS = 'Show the statistics for a sentence with stop words ignored'
EXIT = 'Exit the program'
+
+class Sentiment(Enum):
+ POSITIVE = '+'
+ NEUTRAL = '0'
+ NEGATIVE = '-'
+
+
class Review():
def __init__(self, review_text):
self.review_text = review_text
def get_sentiment_rating(self):
- print(self.review_text)
- pass
+ if self.review_text.split()[0] == '+':
+ return Sentiment.POSITIVE
+ elif self.review_text.split()[0] == '0':
+ return Sentiment.NEUTRAL
+ else:
+ return Sentiment.NEGATIVE
def get_tokens(self):
- print(self.review_text.split())
- pass
-
+ return self.review_text.strip().lower().split()[1:]
+ def token_frequency(self, token):
+ return self.get_tokens().count(token)
def main():
menu_input()
+
def get_data():
- data = ()
try:
with open("sentiment.txt") as file:
- data = file.read()
-
+ return file.readlines()
except FileNotFoundError:
print("File cannot be found")
- return data
+
def get_reviews(data):
- return data.strip().replace("...", "").split('.')
+ reviews = []
+ for review in data:
+ reviews.append(Review(review.strip().replace("...", "")))
+
+ return reviews
+
def get_tokens(data):
- return data.split()
+ return "".join(data).strip().split()
+
def check_token(data):
- tokens = frozenset(data.split())
+ tokens = frozenset(get_tokens(data))
+
token = input("Enter a token: ").lower()
if token in tokens:
print(f"The token \"{token}\" appears in the training data.")
else:
print(f"The token \"{token}\" does not appear in the training data.")
+
def check_document_frequency(data):
- tokens = data.strip().lower().split()
+ tokens = get_tokens(data)
+ print(len(tokens))
token = input("Enter a token: ").lower()
+ print(
+ f"The token \"{token}\" appears {tokens.count(token)} out of {len(tokens)} time(s) in the training data.")
- print(f"The token \"{token}\" appears {tokens.count(token)} out of {len(data)} time(s) in the training data.")
def show_token_stats(data):
- tokens = data.strip().lower().split()
+ print(f"Review num: {len(data)}")
+ reviews = get_reviews(data)
+ tokens = get_tokens(data)
token = input("Enter a token: ").lower()
- stats = ((10 + (10 * (p/maxp) * math.log((p/maxp), 2) )) - (10 + 10 * (n/maxn) * math.log((N/maxn), 2)))
- pass
+ positive_reviews = []
+ positive_tokens = []
+ positive_num = 0
+ highest_positive_num = 0
+ negative_reviews = []
+ negative_tokens = []
+ negative_num = 0
+ highest_negative_num = 0
+ neutral_reviews = []
+ neutral_num = 0
+ all_num = tokens.count(token)
+ # maxp = 0
+
+
+# Separating Positive and Negative reviews and tokens into lists
+ for review in reviews:
+ if(review.get_sentiment_rating() == Sentiment.POSITIVE):
+ positive_reviews.append(review)
+ for review_token in review.get_tokens():
+ positive_tokens.append(review_token)
+ elif(review.get_sentiment_rating() == Sentiment.NEGATIVE):
+ negative_reviews.append(review)
+ for review_token in review.get_tokens():
+ negative_tokens.append(review_token)
+ elif(review.get_sentiment_rating() == Sentiment.NEUTRAL):
+ neutral_reviews.append(review)
+
+
+# Getting total number of Positive and Negative tokens
+ for review in negative_reviews:
+ negative_num += review.get_tokens().count(token)
+
+ for review in neutral_reviews:
+ neutral_num += review.get_tokens().count(token)
+
+ for review in positive_reviews:
+ positive_num += review.get_tokens().count(token)
+
+
+# Get the greatest number of times that any token appears in positive comments
+ # for test_token in frozenset(get_tokens(data)):
+ # for review in positive_reviews:
+ # if review.get_tokens().count(test_token) > highest_positive_num:
+ # highest_positive_num = review.get_tokens().count(test_token)
+
+# Get the greatest number of times that any token appears in negative comments
+ # for test_token in frozenset(get_tokens(data)):
+ # for review in negative_reviews:
+ # if review.get_tokens().count(test_token) > highest_negative_num:
+ # highest_negative_num = review.get_tokens().count(test_token)
+
+ # print(positive_num)
+ # print(highest_positive_num)
+ # print(negative_num)
+ # print(highest_negative_num)
+
+ score = (((10 + 10 * (positive_num/highest_positive_num)) *
+ math.log(len(positive_tokens)/highest_positive_num)) - ((10 + 10 * (negative_num/highest_negative_num)) * math.log(len(negative_tokens)/highest_negative_num)))
+
+ print(f"The token \"{token}\" has {negative_num} negative, {neutral_num} neutral, and {positive_num} positive appearance(s) in the training data.")
+ print(
+ f"The token \"{token}\" has a differential tf-idf score of {score} and is classified as ...")
+
def handle_selection(selection, data):
if selection == MenuOption.SHOW_REVIEWS:
@@ -104,29 +188,43 @@ def menu_input():
except IndexError:
print("Please enter a valid, in range number.")
+
def show_reviews(data):
- reviews = get_reviews(data)
+ review_objects = get_reviews(data)
start_selection = "1"
end_selection = ""
while True:
- start_selection = int(input(f"Enter a review number from {start_selection} to {len(reviews)}: "))
- if start_selection > len(reviews) or start_selection <= 0:
+
+ start_selection = int(
+ input(f"Enter a review number from {start_selection} to {len(review_objects)}: "))
+
+ if start_selection > len(review_objects) or start_selection <= 0 or start_selection == None:
+
print("Please enter a valid, in-range number.")
start_selection = "1"
continue
+
else:
while True:
- end_selection = int(input(f"Enter a review number from {start_selection} to {len(reviews)}: "))
- if end_selection > len(reviews) or end_selection < start_selection:
+
+ end_selection = int(
+ input(f"Enter a review number from {start_selection} to {len(review_objects)}: "))
+
+ if end_selection > len(review_objects) or end_selection < start_selection or end_selection == None:
print("Please enter a valid, in-range number.")
continue
+
else:
+
for review_num in range(start_selection-1, end_selection):
- print(f'Review #{review_num + 1}: {reviews[review_num].strip()}')
+
+ print(
+ f'Review #{review_num + 1}: {review_objects[review_num].review_text}')
+
break
break
-
+
if __name__ == '__main__':
main()
--
GitLab