s444517/ium_444517
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

docker task 2

Browse Source
This commit is contained in:
Kamila 2022-04-03 13:35:05 +02:00
parent 5ee718059f
commit 6f7fe40478
1 changed files with 4 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
data_expl.py
View File

@ -5,7 +5,7 @@ data = pd.read_csv('./googleplaystore.csv')
data.dropna(subset=['Rating', 'Type','Content Rating','Current Ver','Android Ver'], inplace=True) data.dropna(subset=['Rating', 'Type','Content Rating','Current Ver','Android Ver'], inplace=True)
data.reset_index(drop=True, inplace=True) data.reset_index(drop=True, inplace=True)
data.drop(columns=["Size", "Android Ver", "Current Ver", "Last Updated"]) data = data.drop(columns=["Size", "Android Ver", "Current Ver", "Last Updated"])
# normalizing text # normalizing text
to_lowercase = ['App', 'Category', 'Type', 'Content Rating', 'Genres'] to_lowercase = ['App', 'Category', 'Type', 'Content Rating', 'Genres']
@ -34,14 +34,6 @@ np.random.seed(123)
train, validate, test = np.split(data.sample(frac=1, random_state=42), [int(.6*len(data)), int(.8*len(data))]) train, validate, test = np.split(data.sample(frac=1, random_state=42), [int(.6*len(data)), int(.8*len(data))])
print(f"Data shape: {data.shape}\nTrain shape: {train.shape}\nTest shape: {test.shape}\nValidation shape:{validate.shape}") print(f"Data shape: {data.shape}\nTrain shape: {train.shape}\nTest shape: {test.shape}\nValidation shape:{validate.shape}")
f = open("appstrain.csv", "w") train.to_csv('appstrain.csv')
f.write(str(train)) test.to_csv('appstest.csv')
f.close() validate.to_csv('appsvalidate.csv')
f = open("appstest.csv", "w")
f.write(str(test))
f.close()
f = open("appsvalidate.csv", "w")
f.write(str(validate))
f.close()