from google.colab import files
uploaded = files.upload()

import io
df2 = pd.read_csv(io.BytesIO(uploaded['train.csv']))

import pandas as pd
import csv
import matplotlib.pyplot as plt

df = pd.read_csv("train.csv")
df

df.head(5)  # Used to display top 5

df.tail(5) # Used to display last 5

df = pd.read_csv("train.csv", usecols= ["PassengerId", "Survived", "Pclass", "Name", "Sex","Age"])
df.head()

df.describe()

df.sort_values("Age")
df.head()

df = df.sort_values("Age", ascending = False)
df.head(5)

result = df[df['Name'] ==  'Svensson, Mr. Johan'	]
result


df["Sex"].value_counts()


df.nunique()

df_age = df["Age"] < 50
df_sex_mask = df["Sex"] == "female"
df[df_age & df_sex_mask]

df_sex = df["Sex"] == "Male"
df_age_mask = df["Age"] > 70
df[df_sex | df_age_mask]

null_mask = df["Age"].isnull()
df[null_mask]

df.isnull().sum()


df.drop(labels = ["Pclass"], axis=1).head()

df.replace("Nan",df["Age"].median())

df.replace("Masselmani, Mrs. Fatima", "Tanu")


count = df['Survived'].value_counts()
print(count)
# Let us see that in percentage.

percentage = df['Survived'].value_counts() * 100 / len(df)
print(percentage)

%matplotlib inline
color = 0.5
df['Survived'].value_counts().plot(kind = 'bar')