s478831/ium_478831
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
master
ium_478831/IUM_main.ipynb
JulianZablonski ec2a3d1c51 DVC
2022-06-05 14:57:08 +02:00

33 KiB
Raw Permalink Blame History 

!pip install kaggle
!pip install pandas
!pip install seaborn
Requirement already satisfied: kaggle in c:\users\user\anaconda3\lib\site-packages (1.5.12)
Requirement already satisfied: urllib3 in c:\users\user\anaconda3\lib\site-packages (from kaggle) (1.26.7)
Requirement already satisfied: tqdm in c:\users\user\anaconda3\lib\site-packages (from kaggle) (4.64.0)
Requirement already satisfied: python-slugify in c:\users\user\anaconda3\lib\site-packages (from kaggle) (5.0.2)
Requirement already satisfied: requests in c:\users\user\anaconda3\lib\site-packages (from kaggle) (2.26.0)
Requirement already satisfied: six>=1.10 in c:\users\user\anaconda3\lib\site-packages (from kaggle) (1.16.0)
Requirement already satisfied: certifi in c:\users\user\anaconda3\lib\site-packages (from kaggle) (2022.5.18.1)
Requirement already satisfied: python-dateutil in c:\users\user\anaconda3\lib\site-packages (from kaggle) (2.8.2)
Requirement already satisfied: text-unidecode>=1.3 in c:\users\user\anaconda3\lib\site-packages (from python-slugify->kaggle) (1.3)
Requirement already satisfied: charset-normalizer~=2.0.0 in c:\users\user\anaconda3\lib\site-packages (from requests->kaggle) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\users\user\anaconda3\lib\site-packages (from requests->kaggle) (3.2)
Requirement already satisfied: colorama in c:\users\user\anaconda3\lib\site-packages (from tqdm->kaggle) (0.4.4)
Requirement already satisfied: pandas in c:\users\user\anaconda3\lib\site-packages (1.3.4)
Requirement already satisfied: python-dateutil>=2.7.3 in c:\users\user\anaconda3\lib\site-packages (from pandas) (2.8.2)
Requirement already satisfied: pytz>=2017.3 in c:\users\user\anaconda3\lib\site-packages (from pandas) (2021.3)
Requirement already satisfied: numpy>=1.17.3 in c:\users\user\anaconda3\lib\site-packages (from pandas) (1.20.3)
Requirement already satisfied: six>=1.5 in c:\users\user\anaconda3\lib\site-packages (from python-dateutil>=2.7.3->pandas) (1.16.0)
Requirement already satisfied: seaborn in c:\users\user\anaconda3\lib\site-packages (0.11.2)
Requirement already satisfied: pandas>=0.23 in c:\users\user\anaconda3\lib\site-packages (from seaborn) (1.3.4)
Requirement already satisfied: numpy>=1.15 in c:\users\user\anaconda3\lib\site-packages (from seaborn) (1.20.3)
Requirement already satisfied: matplotlib>=2.2 in c:\users\user\anaconda3\lib\site-packages (from seaborn) (3.4.3)
Requirement already satisfied: scipy>=1.0 in c:\users\user\anaconda3\lib\site-packages (from seaborn) (1.7.1)
Requirement already satisfied: pyparsing>=2.2.1 in c:\users\user\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (2.4.7)
Requirement already satisfied: cycler>=0.10 in c:\users\user\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (0.10.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\user\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (1.3.1)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\user\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (2.8.2)
Requirement already satisfied: pillow>=6.2.0 in c:\users\user\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (8.4.0)
Requirement already satisfied: six in c:\users\user\anaconda3\lib\site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.16.0)
Requirement already satisfied: pytz>=2017.3 in c:\users\user\anaconda3\lib\site-packages (from pandas>=0.23->seaborn) (2021.3)

!kaggle datasets download -d wenruliu/adult-income-dataset

    
401 - Unauthorized

!unzip -o adult-income-dataset.zip
'unzip' is not recognized as an internal or external command,
operable program or batch file.

import pandas as pd
df=pd.read_csv('adult-income-dataset.csv')
df
age workclass fnlwgt education educational-num marital-status occupation relationship race gender capital-gain capital-loss hours-per-week native-country income
0 25 Private 226802 11th 7 Never-married Machine-op-inspct Own-child Black Male 0 0 40 United-States <=50K
1 38 Private 89814 HS-grad 9 Married-civ-spouse Farming-fishing Husband White Male 0 0 50 United-States <=50K
2 28 Local-gov 336951 Assoc-acdm 12 Married-civ-spouse Protective-serv Husband White Male 0 0 40 United-States >50K
3 44 Private 160323 Some-college 10 Married-civ-spouse Machine-op-inspct Husband Black Male 7688 0 40 United-States >50K
4 18 ? 103497 Some-college 10 Never-married ? Own-child White Female 0 0 30 United-States <=50K
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
48837 27 Private 257302 Assoc-acdm 12 Married-civ-spouse Tech-support Wife White Female 0 0 38 United-States <=50K
48838 40 Private 154374 HS-grad 9 Married-civ-spouse Machine-op-inspct Husband White Male 0 0 40 United-States >50K
48839 58 Private 151910 HS-grad 9 Widowed Adm-clerical Unmarried White Female 0 0 40 United-States <=50K
48840 22 Private 201490 HS-grad 9 Never-married Adm-clerical Own-child White Male 0 0 20 United-States <=50K
48841 52 Self-emp-inc 287927 HS-grad 9 Married-civ-spouse Exec-managerial Wife White Female 15024 0 40 United-States >50K

48842 rows × 15 columns

df['income_if_<=50k'] = df['income'].apply(lambda x: True if x == '<=50K' else False)
df['if_male'] = df['gender'].apply(lambda x: True if x == 'Male' else False)
df['income_if_<=50k']= df['income_if_<=50k'].astype(int)
df['if_male']= df['if_male'].astype(int)

#usunięcie nie pełnych danych 
df = df[df.workclass != '?']
df = df.reset_index(drop=True)
df
age workclass fnlwgt education educational-num marital-status occupation relationship race gender capital-gain capital-loss hours-per-week native-country income income_if_<=50k if_male
0 25 Private 226802 11th 7 Never-married Machine-op-inspct Own-child Black Male 0 0 40 United-States <=50K 1 1
1 38 Private 89814 HS-grad 9 Married-civ-spouse Farming-fishing Husband White Male 0 0 50 United-States <=50K 1 1
2 28 Local-gov 336951 Assoc-acdm 12 Married-civ-spouse Protective-serv Husband White Male 0 0 40 United-States >50K 0 1
3 44 Private 160323 Some-college 10 Married-civ-spouse Machine-op-inspct Husband Black Male 7688 0 40 United-States >50K 0 1
4 34 Private 198693 10th 6 Never-married Other-service Not-in-family White Male 0 0 30 United-States <=50K 1 1
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
46038 27 Private 257302 Assoc-acdm 12 Married-civ-spouse Tech-support Wife White Female 0 0 38 United-States <=50K 1 0
46039 40 Private 154374 HS-grad 9 Married-civ-spouse Machine-op-inspct Husband White Male 0 0 40 United-States >50K 0 1
46040 58 Private 151910 HS-grad 9 Widowed Adm-clerical Unmarried White Female 0 0 40 United-States <=50K 1 0
46041 22 Private 201490 HS-grad 9 Never-married Adm-clerical Own-child White Male 0 0 20 United-States <=50K 1 1
46042 52 Self-emp-inc 287927 HS-grad 9 Married-civ-spouse Exec-managerial Wife White Female 15024 0 40 United-States >50K 0 0

46043 rows × 17 columns

import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
X, y = df[['age']], df['income_if_<=50k']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=37)
n_samples, n_features = X.shape
X_train = np.array(X_train).reshape(-1,1)
X_test = np.array(X_test).reshape(-1,1)
y_train = np.array(y_train).reshape(-1,1)
y_test = np.array(y_test).reshape(-1,1)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.fit_transform(X_test)


import torch
torch.from_file
X_train = torch.from_numpy(X_train.astype(np.float32))
X_test = torch.from_numpy(X_test.astype(np.float32))
y_train = torch.from_numpy(y_train.astype(np.float32))
y_test = torch.from_numpy(y_test.astype(np.float32))

y_train = y_train.view(y_train.shape[0], 1)
y_test= y_test.view(y_test.shape[0], 1)

import torch.nn as nn
class LogisticRegresion(nn.Module):
    def __init__(self, n_input_featuers):
        super(LogisticRegresion, self).__init__()
        self.linear = nn.Linear(n_input_featuers, 1)
    
    def forward(self, x):
        y_predicted = torch.sigmoid(self.linear(x))
        return y_predicted

model = LogisticRegresion(n_features)
criterion = nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
num_epochs = 1500
for epoch in range(num_epochs):
    y_predicted = model(X_train)
    loss = criterion(y_predicted,y_train)
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

    if (epoch%100==0):
        print(f'epoch:{epoch+1},loss = {loss.item():.4f}')
epoch:1,loss = 0.5776
epoch:101,loss = 0.5632
epoch:201,loss = 0.5538
epoch:301,loss = 0.5475
epoch:401,loss = 0.5432
epoch:501,loss = 0.5402
epoch:601,loss = 0.5381
epoch:701,loss = 0.5366
epoch:801,loss = 0.5356
epoch:901,loss = 0.5348
epoch:1001,loss = 0.5342
epoch:1101,loss = 0.5338
epoch:1201,loss = 0.5335
epoch:1301,loss = 0.5333
epoch:1401,loss = 0.5332

with torch.no_grad():
    y_predicted = model(X_test)
    y_predicted_cls = y_predicted.round()
    acc = y_predicted_cls.eq(y_test).sum()/float(y_test.shape[0])
    print(f'{acc:.4f}')
0.7412

result = open("result_pytorch",'w+')
result.write(f'acc:{acc:.4f}')
10