# import all the required libraries import numpy as np import pandas as pd # import matplotlib.pyplot as plt # from sklearn.preprocessing import MinMaxScaler # import scipy as sp # read data from the data set ds1 = pd.read_csv("dataset.csv") # ds2 = pd.read_json("json_filename") # ds3 = pd.read_text("text_filename") # ds4 = pd.read_excel("xlsx_filename") # ds5 = pd.read_html("html_filename") # ds6 = pd.read_xml("xml_filename") # PERFORM OPERATIONS ON THE DATA FRAME # print(ds1.head()) # print(ds1.tail()) # print("Shape:", ds1.shape) # print("Columns:", ds1.columns) # print("Describe:", ds1.describe()) # print(ds1.info()) # print("Size:", ds1.size) # print("isna: \n",ds1.isna().sum()) # isna().sum() # print("isnull: \n",ds1.isnull().sum()) #print(ds1.info()) # isnull: gender NationalITy ... StudentAbsenceDays Class # 0 False False ... False False # 1 False False ... False False # 2 False False ... False False # 3 False False ... False False # 4 False False ... False False # .. ... ... ... ... ... # 475 False False ... False False # 476 False False ... False False # 477 False False ... False False # 478 False False ... False False # 479 False False ... False False ds1['raisehands']= ds1['raisedhands'].astype('int64') #print(ds1.dtypes) #print(ds1.dtypes) #print(ds1.dtypes['ssc_p']) #di = {'Roll':[1,2,3,4,5], #'Name':['a','b','c','d','e']} #ds1 = pd.DataFrame(di) #print(ds1) #output #ds1['Roll'].replace([1], [], inplace = True) #print(ds1) #print(ds1.interpolate().count()) #print(ds1.interpolate()) ds1{'raisedhands'} =ds1