import numpy as np
import pandas as pd
import ProjectUitlities.Utils as Utils
data = {
"fname": ["Sumit", "Isha"],
"lname": ["Chauhan", "Khattar"],
"Age": [31, 31]
}
df1 = pd.DataFrame(data)
Utils.printSpaces("Original dataframe")
print(df1)
Utils.printSpaces(
"filter where name is Sumit \n rows not matching the columns will be converted to null"
)
print(df1.where(df1["fname"] == "Sumit").dropna())
Utils.printSpaces("using queries , age >30 ")
print(df1.query("Age > 30"))
Utils.printSpaces("using queries , fname is Sumit ")
print(df1.query("fname == 'Sumit' "))
# cov() Method is used to find covariance of two series
import numpy as np
import pandas as pd
import ProjectUitlities.Utils as Utils
import matplotlib.pyplot as plt
data = np.array([1, 2, 1, 4, 5])
ser = pd.Series(data=data)
print(ser.add(1))
print(ser.mul(2))
print(ser.mul([1, 2, 3, 4, 5]))
Utils.printSpaces("selecting top 2 rows")
print(ser.head(2))
ser.plot()
# sudo apt-get install python-tk
# sudo apt-get install python3-tk
# plt.show()
Utils.printSpaces("map function can take lambdas")
squared = ser.map(lambda x: x**2)
print(squared)
Utils.printSpaces("to filter the value based on data")
print(squared[squared > 10])
Utils.printSpaces("filter() method works on index and not data")
names = ["Sumit", "Chauhan", "Male", 31]
import pandas as pd
import numpy as np
import ProjectUitlities.Utils as Utils
Utils.printSpaces("Creating series from arrays")
data = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
ser = pd.Series(data)
print(ser)
Utils.printSpaces("Creating series from lists")
list = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
ser = pd.Series(list)
print(ser)
Utils.printSpaces("Accessing Element from Series with Position")
print(ser[:5])
Utils.printSpaces("Accessing Element Using Label(index)")
ser = pd.Series(data)
print(ser[3])
import pandas as pd
import ProjectUitlities.Utils as Utils
# dictionary of lists
dict = {'name': ["aparna", "pankaj", "sudhir", "Geeku"],
'degree': ["MBA", "BCA", "M.Tech", "MBA"],
'score': [90, 40, 80, 98]}
# creating a dataframe from a dictionary
df = pd.DataFrame(dict)
# iterating over rows using iterrows() function
Utils.printSpaces("data frame iterationss using iterrows")
for i, j in df.iterrows():
print(f'dataframa indes {i} with data: \n {j} \n')
print()
Utils.printSpaces("Iterating Columns ")
columns = list(df)
print(df)
print(f'columns are {columns}')
for i in columns:
# printing the third element of the column
print(df[i][2])
Utils.printSpaces("printing second row ")
print(df.iloc[1])
Utils.printSpaces("fetching second Columns ")
print(df[df.columns[2]])
import collections
import ProjectUitlities.Utils as Utils
# The combined dictionary contains the key and value pairs in a specific sequence eliminating any duplicate keys.
# The best use of ChainMap is to search through multiple dictionaries at a time and
# get the proper key-value pair mapping.
dict1 = {'name': 'Sumit', 'lname': 'Chauhan'}
dict2 = {'name': 'Isha', 'lname': 'Khattar', 'age': 31}
combined = collections.ChainMap(dict1, dict2) # order of it is important. First pair of keys are taken incase of
# duplicate values. this shows that chain map acts like a kind of a stack
print(combined)
# If there are duplicate keys, then only the value from the first key is preserved.
print('Keys = {}'.format(list(combined.keys())))
print('Values = {}'.format(list(combined.values())))
print(combined.get('name'))
Utils.printSpaces("updating chain maps")
print('just update the dictionary used to create the chained map and it will be done automatically')
dict1['gender'] = 'male'
print('Keys = {}'.format(list(combined.keys())))
print('Values = {}'.format(list(combined.values())))
# importing numpy as np
import numpy as np
from ProjectUitlities import Utils
# dictionary of lists
dict = {
'First Score': [100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score': [np.nan, 40, 80, 98]
}
# creating a dataframe from dictionary
df = pd.DataFrame(dict)
Utils.printSpaces("data cleaning ")
Utils.printSpaces("filling nulls")
# filling missing value using fillna()
# inplace is set to false which means data will not be changed in original dataframes
print(df.fillna(0, inplace=False))
Utils.printSpaces("dropping nulls")
# filling missing value using fillna()
# inplace is set to false which means data will not be changed in original dataframes
print(
df.dropna()
) # by default axis is 0 which means all the rows containing null will be dropped.
Utils.printSpaces("dropping columns nulls")
# filling missing value using fillna()
import ProjectUitlities.Utils as Utils
Utils.printSpaces("Finding duplicate of 5")
d = [1, 2, 3, 4, 5, 6, 7, 7, 88, 9, 2, 32, 3, 4, 5, 1]
if len(list(filter(lambda x: x == 5, d))) > 1:
print('there is a duplicate 5')
else:
print('5 was not duplicated in the list')
Utils.printSpaces("Change things to upper case ")
d = ['sumit', 'chauhan']
print(list(map(lambda x: x.upper(), d)))