import pandas as pd
df_smokeban = pd.read_csv('SmokeBan.csv')
#had a column of data on Jupyter that did no exist in original .csv file
df_smokeban = df_smokeban.drop('Unnamed: 0', axis=1)
df_smokeban.head()
smoker | ban | age | education | afam | hispanic | gender | |
---|---|---|---|---|---|---|---|
0 | yes | yes | 41 | hs | no | no | female |
1 | yes | yes | 44 | some college | no | no | female |
2 | no | no | 19 | some college | no | no | female |
3 | yes | no | 29 | hs | no | no | female |
4 | no | yes | 28 | some college | no | no | female |
smokeban_dict = {"smoker": "identifies whether the person is a smoker",
"ban": "identifies whether there is a smoking ban in their area",
"age": "person's age",
"education": "person's highest level of education",
"afam": "whether the person identifies as African American",
"hispanic": "whether the person identifies as Hispanic",
"gender": "gender that the person identifies with"}