Tips - Analyze

import seaborn as sns
df = sns.load_dataset('tips')
df.head()

   total_bill   tip     sex smoker  day    time  size
0       16.99  1.01  Female     No  Sun  Dinner     2
1       10.34  1.66    Male     No  Sun  Dinner     3
2       21.01  3.50    Male     No  Sun  Dinner     3
3       23.68  3.31    Male     No  Sun  Dinner     2
4       24.59  3.61  Female     No  Sun  Dinner     4

df.info()

RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
 #   Column      Non-Null Count  Dtype   
---  ------      --------------  -----   
 0   total_bill  244 non-null    float64 
 1   tip         244 non-null    float64 
 2   sex         244 non-null    category
 3   smoker      244 non-null    category
 4   day         244 non-null    category
 5   time        244 non-null    category
 6   size        244 non-null    int64   
dtypes: category(4), float64(2), int64(1)
memory usage: 7.4 KB

df.describe()

       total_bill         tip        size
count  244.000000  244.000000  244.000000
mean    19.785943    2.998279    2.569672
std      8.902412    1.383638    0.951100
min      3.070000    1.000000    1.000000
25%     13.347500    2.000000    2.000000
50%     17.795000    2.900000    2.000000
75%     24.127500    3.562500    3.000000
max     50.810000   10.000000    6.000000

df['sex'].value_counts(normalize=False, sort=True, ascending=False)

sex
Male      157
Female     87
Name: count, dtype: int64

df['sex'].value_counts(normalize=True, sort=True, ascending=False)

sex
Male      0.643443
Female    0.356557
Name: proportion, dtype: float64

df['sex'].value_counts(normalize=False, sort=True, ascending=False).plot(kind='bar')

sns.countplot(data=df, x='sex')

df['tip'].describe()

count    244.000000
mean       2.998279
std        1.383638
min        1.000000
25%        2.000000
50%        2.900000
75%        3.562500
max       10.000000
Name: tip, dtype: float64

df['tip'].mean()

2.99827868852459

df['tip'].median()

2.9

df['tip'].var()

1.914454638062471

df['tip'].std()

1.3836381890011822

df['tip'].min()

1.0

df['tip'].max()

10.0

df['tip'].plot(kind='hist', bins=20)

sns.displot(data=df, x='tip', bins=20)

df['tip'].plot(kind='box')

fig, ax = plt.subplots(figsize=(10, 2))
sns.catplot(data=df, y='tip', kind='box')

pd.crosstab(df['sex'], df['smoker'])

smoker  Yes  No
sex            
Male     60  97
Female   33  54

pd.crosstab(df['sex'], df['smoker'], normalize=True)

smoker       Yes        No
sex                       
Male    0.245902  0.397541
Female  0.135246  0.221311

sns.heatmap(pd.crosstab(df['sex'], df['smoker']), annot=True)

sns.heatmap(pd.crosstab(df['size'], df['day']), annot=True)

df.groupby('sex')['tip'].describe()

        count      mean       std  min  25%   50%   75%   max
sex                                                          
Male    157.0  3.089618  1.489102  1.0  2.0  3.00  3.76  10.0
Female   87.0  2.833448  1.159495  1.0  2.0  2.75  3.50   6.5

df.groupby('sex')['tip'].mean()

sex
Male      3.089618
Female    2.833448
Name: tip, dtype: float64

df.groupby('sex')['tip'].median()

sex
Male      3.00
Female    2.75
Name: tip, dtype: float64

df.groupby('sex')['tip'].mean().plot(kind='bar')

sns.catplot(data=df, x='sex', y='tip', kind='bar')

sns.displot(data=df, x='tip', hue='sex')

sns.catplot(data=df, x='tip', hue='sex', kind='box')

plt.scatter(df['tip'], df['total_bill'])

sns.scatterplot(data=df, x='tip', y='total_bill')