Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
4 years ago

##Download and Explore Data

import pandas as pd
import numpy as np
import seaborn as sns
import torch
from torch.utils.data import TensorDataset, random_split, DataLoader
import torchvision.models as models
import matplotlib.pyplot as plt
from sklearn.metrics import f1_score
import torch.nn.functional as F
import torch.nn as nn
%matplotlib inline
/usr/local/lib/python3.6/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead. import pandas.util.testing as tm 
from google.colab import drive
drive.mount('/content/gdrive')
path = "/content/gdrive/My Drive/Colab Notebooks/data/employee_compensation_sf.csv"
Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount("/content/gdrive", force_remount=True). 
df = pd.read_csv(path)
print(df.shape)
df.head()
(291825, 22) 
df.columns
Index(['year_type', 'year', 'organization_group_code', 'organization_group',
       'department_code', 'department', 'union_code', 'union',
       'job_family_code', 'job_family', 'job_code', 'job',
       'employee_identifier', 'salaries', 'overtime', 'other_salaries',
       'total_salary', 'retirement', 'health_dental', 'other_benefits',
       'total_benefits', 'total_compensation'],
      dtype='object')