s434780/ium_434780
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

task(UM_03) Tweaks in main

Browse Source
This commit is contained in:
sadurska@trui.pl 2021-04-17 21:53:31 +02:00
parent 78c8da15a8
commit 5484926efc
2 changed files with 5005 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
main.py
View File

@ -3,7 +3,7 @@ from sklearn.model_selection import train_test_split
def main(): def main():
data = pd.read_csv('resources/data.csv', header=0, sep=',') data = pd.read_csv('resources/Amazon_Consumer_Reviews.csv', header=0, sep=',')
columns = ['reviews.date', 'reviews.numHelpful', 'reviews.rating', 'reviews.doRecommend'] columns = ['reviews.date', 'reviews.numHelpful', 'reviews.rating', 'reviews.doRecommend']
string_columns = ['name', 'brand', 'categories', 'primaryCategories', 'keys', 'manufacturer', 'reviews.title', string_columns = ['name', 'brand', 'categories', 'primaryCategories', 'keys', 'manufacturer', 'reviews.title',
@ -14,7 +14,8 @@ def main():
for c in string_columns: for c in string_columns:
data[c] = data[c].str.lower() data[c] = data[c].str.lower()
# print(data.isnull().sum()) print("Empty rows summary:")
print(data.isnull().sum())
data.dropna() data.dropna()
data.to_csv('resources/data.csv') data.to_csv('resources/data.csv')
@ -25,7 +26,7 @@ def main():
train.to_csv('resources/train.csv') train.to_csv('resources/train.csv')
dev.to_csv('resources/dev.csv') dev.to_csv('resources/dev.csv')
print("Mean reviews rating for each primary category: ") print("\n\nMean reviews rating for each primary category: ")
print(data[["primaryCategories", "reviews.rating"]].groupby("primaryCategories").mean()) print(data[["primaryCategories", "reviews.rating"]].groupby("primaryCategories").mean())
print("\n\nCounted primary categories: ") print("\n\nCounted primary categories: ")

5001
resources/Amazon_Consumer_Reviews.csv Normal file
View File

File diff suppressed because one or more lines are too long