Assg25

import pandas as pd
df=pd.read_csv("covid_19_india.csv")

print(df)

#detecting NA values
df.isnull()

import numpy as np
missing_values=["N/a","na",np.nan,0]
df=pd.read_csv("covid_19_india.csv",na_values=missing_values)
df

df.isnull()

df.isnull().sum()

import seaborn as sns
sns.heatmap(df.isnull(),yticklabels=False)

#removing NA values
df.dropna()

df.dropna(how='all')

#filling data
df.fillna(0)

df_next=df.fillna(method='bfill')
df_next

df.interpolate()

#transforming data
df.drop(['Date','Time'],axis=1)

from pandas import DataFrame
series_obj=Series(np.arange(6))
series_obj.name="added_variable"
series_obj

added=DataFrame.join(df,series_obj)
added

#sorting
print(df_next.sort_values(['Cured','Confirmed'], ascending=True))

import matplotlib.pyplot as plt
x=df_next['Confirmed']
plt.hist(x,bins=25,color='green',edgecolor='blue',alpha=0.5)
plt.title("Histogram")
plt.xlabel('Cured')
plt.ylabel('Deaths')

x=df['Cured']
y=df['Deaths']
plt.scatter(x,y,c=df['Cured'], s=df['Deaths'],marker='D',alpha=0.4)