import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
df=sns.load_dataset("tips")
print(df)

df.isnull().sum()

plt.figure(figsize=(5,5))
plt.title("data with outliners")
df.boxplot()
plt.show()

plt.figure(figsize=(5,5))
cols=["size","tip","total_bill"]
q1=df[cols].quantile(0.25)
q3=df[cols].quantile(0.75)
iqr=q3-q1
df=df[~((df[cols]<(q1-1.5*iqr))|(df[cols]>(q3+1.5*iqr))).any(axis=1)]
plt.title("dataset after removing outliners")
df.boxplot()
plt.show()

sns.barplot(x=df["day"],y=df["total_bill"],hue=df["day"])
plt.legend(loc="center")
plt.title("highest total bill amount by day of the week")

sns.boxplot(x=df["smoker"],y=df["tip"],hue=df["smoker"])
plt.title("average tip amount given by smokers and non-smokers")

df["tip_percent"]=df["tip"] / df["total_bill"]
sns.scatterplot(x=df['size'], y=df['tip_percent'],data=df)
plt.title("Tip Percentage by Dining Party Size")

sns.boxplot(x=df["sex"],y=df["tip"],hue=df["sex"])
plt.title("tips based on gender")

sns.scatterplot(x=df["day"],y=df["total_bill"],hue=df["day"])
plt.legend(loc="best")
plt.title("total bill amount by day of te week")

sns.histplot(data=df, x="total_bill", hue="time", element="step", stat="density")
plt.title("Distribution of Total Bill Amounts by Time of Day")
plt.show()

sns.barplot(x=df["size"],y=df["total_bill"],hue=df["size"])
plt.title("average total bill amount by dinning party size")

sns.boxplot(x="day", y="tip", data=df)
plt.title("Tip Amount by Day of Week")
plt.show()

sns.violinplot(x="time",y="tip",data=df)
plt.title("tip amount time of day")

sns.scatterplot(x="total_bill",y="tip",data=df)
plt.title("Correlation between Tip Amount and Total Bill Amount")
plt.show()