Box Plot for All Column

 plt.figure(figsize=(10,10))

sns.boxplot(data=df)
plt.show()

List to Dictionary to DataFrame

#List

height = [151, 174, 138, 186, 128, 136, 179, 163, 152, 131]

weight = [63, 81, 56, 91, 47, 57, 76, 72, 62, 48]

##List to Dictionary

baby_dic = {'height':height,'weight':weight} 

#dictionary to DataFrame

baby_data = pd.DataFrame(baby_dic)

Outlier Detecting in Pandas

 Q1 = df_boston['CRIM'].quantile(0.25)

Q3 = df_boston['CRIM'].quantile(0.75)

IQR = Q3 - Q1

Outlier_min = Q1 - 1.5 * IQR 

Outlier_max = Q3 + 1.5 * IQR

print(IQR, Outlier_min, Outlier_max)

###outlier dealing

df_boston['CRIM'] = np.where(df_boston['CRIM']>= Outlier_max, Outlier_max,df_boston['CRIM'])

df_boston['CRIM'] = np.where(df_boston['CRIM']<= Outlier_min, Outlier_min,df_boston['CRIM'])

Pandas Series and Dataframe

 # Series from list

a = [4, 100, 45, 32, 7, 2]

example1 = pd.Series(a)

print(example1)

# Series with index

example2 = pd.Series(a, index = ["a", "b", "c","d","e","f"])

# Series from Data Dictionary

datadict = {"data1": 420, "data2": 380, "data3": 390}

example3 = pd.Series(datadict)

# Dataframe from list

data = [['Alex',10],['Bob',12],['Clarke',13]]

df1 = pd.DataFrame(data,columns=['Name','Age'])

df1

# Add new Column in Dataframe

df2['Address'] = pd.Series(['Mumbai','Pune','Delhi'])

# Add new rows

data = [['Ehsan',10,'Mumbai'],['Rahman',12,'Goa'],['Himlu',13,'Milan']]

df3 = pd.DataFrame(data,columns=['Name','Age','Address'])

df = df2.append(df3)

df

Usefull Pandas Statical Formula

 #data.sex.describe()

Describinf sing Column

#data.std()

For Standard Deviation

#Skewness and Kurtosis

print(skew(data.pollution_exp, axis=0, bias=True))

print(kurtosis(data.pollution_exp, axis=0, bias=True))

Some Usefull Pandas Formula

 # data.info()

use for displaying Column Name,[Data type], null/Non/Null

#data.describe().T

use to display Mean,Median Mode, Percentile,Min and max Value

#data.corr().style.background_gradient(cmap='coolwarm')

use to Display and Calculate Correlation among Columns,

#data.isna()

for finding null value in columns

#data.isna().sum()

for displaying total null values in columns

#data['classification'].unique()

to display Unique Value

#data[['classification','id']].groupby('classification').count()

to display Count value group by naother column

#data.drop(['id','rbc'],axis=1,inplace=True)

droping Columns

#data['age'].mean()

calculating Mean of Column

#data['dm'].replace(to_replace = {' yes':'yes'},inplace=True)

replacing a value with another value

#data['appet'].fillna( data['appet'].mode()[0], inplace=True)

Filling Null Value with Mode

# for col in data.columns:

    print(f"{col} has {data[col].unique()} values\n")

Displaying all columns Unique Value

#

g = sns.PairGrid(data)

g.map_diag(plt.hist)

g.map_offdiag(plt.scatter)

Displaying Pair Plot

#sns.catplot(x="classification", y="age",data=data,hue='appet',col='htn')

Displaying Category Plot

#sns.boxplot(x='htn',y='age',data=notchk_age)

Displaying Box Plot

Google Drive access from Google Colab

 import pandas as pd

from google.colab import drive

drive.mount('/content/drive')

data= pd.read_csv('/content/drive/MyDrive/DataScience/Content/kidney_disease.csv')

data.head()