#Practical 1 (Write a program in python to display the execution of Lists - Demo the use of append(), insert(),extend(), remove(), pop().)

A=[1,23,"Learning","Python"]
print("All Elements in the list : ", A)

#Append Function
A.append(6)
print("Appended List : ",A)

#Insert Function
A.insert(2,"Practical 1")
print("Inserted Element : ",A)

#Remove Function
A.remove(23)
print("Updated list after removal : ",A)

#Pop Function (Delete value from specified index)
A.pop(0)
print("Updated list after pop : ",A)

#Extend Function
B=["Class","Sybsc A"]
A.extend(B)
print("Extended list : ",A)



#Practical 2 (Write a program in python to display the execution of Tuples. Create a student attendance table to demo the use of tuples.)

tup=()
start=1
while(start):
  name=input("Enter your Name : ")
  rollno=input("Enter your Roll No. : ")
  lec_attended=input("Enter Total Lectures Attended : ")
  student=("Name : "+name,"Roll No. : "+rollno,"Lec Attented : "+lec_attended)
  tup+=student
  req=int(input("To continue press 1,To view details press 2 : "))
  if(req==1):
    start=1
  else:
    print(tup)
    start=0


#Practical 3.1 (Write a program in python to display the execution of Sets.)
print("Mohit.K 1129\n")
set1=set()
set2=set()

#To add values in set1 in the range of 5
for i in range(5):
  set1.add(i)
print("set1 : ",set1)

#To add(insert) elements in set2 in range between 3 to 9
for i in range(3,9):
  set2.add(i)
print("set2 : ",set2)

# Intersection of set1 and set2
set3 = set1.intersection(set2)
print("\nIntersection using intersection() function of set1 & set2")
print("set3 : ",set3)

# Intersection using "&" operator
set4 = set1 & set2
print("\nIntersection using '&' operator")
print("set 4 : ",set4)

#Union Function
print("\nUnion of set1 & set2")
set5 = set1.union(set2)
print("set5 : ",set5)

#Differnece between set1 & set2
print("\nDiffernce between set1 & set2")
set6 = set1.difference(set2)
print("set6 : ",set6)

#Difference using "-(minus)" operator
print("\nDiffference using - operator")
set7 = set1-set2
print("set7 : ",set7)

#Clearing the values
print("\nClearing set1 & set2")
set1.clear()
print(set1)
set2.clear()
print(set2)



#Practical 3.2 (Demo the use of sets to display employee records of a company.)

start=1
employeedetails = {"""  """}
while(start):
    empid = input("Enter Employee ID : ")
    name = input("Enter Employee Name : ")
    joiningdate = input("Enter joining date in dd/mm/yy formaat : ")
    dept = input("Enter Hiring department : ")
    annualsalary = input("Enter annual salary : ")
    employee = ("Empid  "+empid,"Name "+name, "Joing Date  "+joiningdate, " Department "+dept, "Annual salary " +annualsalary)
    print(employee)
    employeedetails.add(employee)
    req = int(input("Enter 1 to add more employee details else Enter 2 to display the info"))
    if(req == 1):
        start = 1
    else:
        print("All Employee details are \n")
        print(employeedetails)
        start = 0



#Practical 4 (Write a program in python to display the execution of Dictionary. Create a dictionary set of and find the employee having highest and lowest salary.)


dict1 = {"Name" : "Mohit","Age" : "20","Location" : "Mumbai"}
dict2 = {"Height" : "5'11"}
print("dict1 : ",dict1)
print("dict2 : ",dict2)

#To print keys
print("\nPrinting Keys of dict1")
print(dict1.keys())

#To print values of key-value pair
print("\nPrinting values of dict1")
print(dict1.values())

#To update data of values
print("\n Updated Height of dict2")
dict2["Height"]="6'0"
print(dict2)

#To append dict2 in dict1
print("\nAppending dict2 in dict1")
dict1.update(dict2)
print(dict1)

#To remove any data from dictonary
print("\nRemoved Location")
dict1.pop("Location")
print(dict1)

#To print min and max salary of an employee
salary = {"Mohit" : 850000,"Hardik" : 780000,"Kaushik" : 650000}

#To print Highest & Lowest Salary of an employee
print("\nEmployee with Highest Salary : ",max(salary,key=salary.get))
max_sal = max(salary,key=salary.get)
print(salary.get(max_sal))
print("\nEmployee with Lowest Salary : ",min(salary,key=salary.get))
min_sal = min(salary,key=salary.get)
print(salary.get(min_sal))



#Practical 5 (Write a program in python to display the execution of Strings. Perform concat, iteration,membership and methods like upper(), join(), split(), find(), replace().)



s0 = "Orange"
s1 = "Hello this is python language"
s2 = "Lets learn about strings in python"
#CONCATENATING --> Adding two strings together
print("----THIS IS CONCATENATION----")
print(s1 + s2)       #this is simply concatenating using + operator
print(s1 + ',' + s2) #to make it look good
#ITERAING --> Going through the string character by character
print("----THIS IS ITERATING----")
for i in s0:
  print(i)
#upper() --> It will turn string to uppercase
print("----UPPERCASE----")
print(s0.upper())
#lower() --> It will turn string to lowercase
print("----LOWERCASE----")
print(s0.lower())
#len() --> To find length of string
print("----LENGTH----")
print("Length of s1 : ",len(s1))
#join() --> It will join the other string
str1 = '->'
str2 = 'Hello'
print("----JOINING----")
print(str1.join(str2))
string = 'Mohit'
print( '' + '.'.join(string))
#split() --> It will split the string word by word
print("----SPLITING----")
print(s1.split())
print(s1.split(" ",2))
#find() --> It will find the character or word and return its index
print("----FINDING----")
print(s1.find('python'))
#replace() --> It will replace string with new string
print("----REPLACING learn----")
print(s2.replace('learn','study'))




#Practical 6 (Compute a program in python using Matploitlib usage.)

from google.colab import files
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
df = files.upload()
df = pd.read_csv(r'Pokemon.csv') #usage of pandas
df.head()
df.drop('#', inplace=True, axis=1)
df.head()
df.shape #usage of numpy
df.info()
newdf = pd.DataFrame(df, columns=['Name','HP'])
newdf.head()
newdf.shape
plt.rcParams["figure.figsize"] = (10, 4)
plt.bar(newdf['Name'].head(), newdf['HP'].head())
plt.show()


 # Line Plot

import numpy as np
import matplotlib.pyplot as plt

x = np.arange(11)
print(x)
y = 2*x
print(y)
plt.plot(x,y)
plt.title("Line Plot")
plt.xlabel("X Label")
plt.ylabel("Y Label")

# Adding two line in same plot

import numpy as np
import matplotlib.pyplot as plt

x = np.arange(11)
y1 = 2*x
y2 = 3*x

print("\n","x  : ",x,"\n\n","y1 : ",y1,"\n","y2 : ",y2)
plt.plot(x,y1,color="g")
plt.plot(x,y2,color="r")
plt.title("Two Line Plot")
plt.xlabel("X Label")
plt.ylabel("Y Label")
plt.grid("True")

# Adding multiple plot in same screen

import numpy as np
import matplotlib.pyplot as plt

x = np.arange(11)
y1 = 2*x
y2 = 3*x

plt.subplot(3,3,1)  #Subplot syntax (row,col,index of graph)
plt.plot(x,y1,color='g',linestyle=':')
plt.subplot(3,3,7)
plt.plot(x,y2,color='b')

#Bar Plot

import numpy as np
import matplotlib.pyplot as plt

#define a dictionary for student marks
student = {"Bob":87,"Matt":56,"Arpit":18}
names = list(student.keys())
marks = list(student.values())
plt.bar(names,marks)  #For Horizontal bar graph type "plt.barh(names,marks)"
plt.title("Students Mark Graph")
plt.xlabel("Student Names")
plt.ylabel("Student Marks")


#Scatter Plot

import numpy as np
import matplotlib.pyplot as plt

x = np.arange(1,21)
y = np.arange(6,26)
y2 = np.arange(10,30)

plt.scatter(x,y,marker="*",c="g",s=100)  #marker means can add any symbol to show on graph,c=color,s=size
plt.scatter(x,y2,marker="^",c="r",s=50)

plt.plot()


#hist graph
import matplotlib.pyplot as plt
data=[1,2,2,2,3,3,3,3,9,9,4,8,4]
plt.hist(data,color='orange')

#pie chart with numbers
import matplotlib.pyplot as plt
fruit=["Apple","Mango","Banana","Guava"]
quantity=[64,66,22,78]
plt.pie(quantity,labels=fruit)

# with percentage
import matplotlib.pyplot as plt
quantity=[55,34,22,78,21]
vegetable=["Potatu","Tomatu","Tindi","Lauki","Bindi 12 rupey"]
plt.pie(quantity,labels=vegetable,autopct='%0.1f',colors=['Yellow','Green','Orange','Red','Blue'])
plt.pie([1],colors=['black'],radius=0.4)




import matplotlib.pyplot as plt
x = [5,2,9,4,7]
y = [10,6,8,4,2]
plt.xlabel("x value")
plt.ylabel("y value")

# Bar Graph
plt.bar(x,y)

# Scatter Graph
plt.scatter(x,y,marker="*",c="r",s=100)

# Histogram Graph
plt.hist(x,color="green")


import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
df=pd.DataFrame(np.random.rand(10,5))
Columns = ['A','B','C','D','E']
df.plot.area()
plt.legend(["A","B","C","D","E"])
plt.show()



# Practical 7 (Compute a program in python using Numpy usage.)

import numpy as np

# 1 Dimensional Array
l = [1,9,8,5,3]
npl = np.array(l)
print("1 Dimensional Array :\n",npl)
print("Matrix : ",npl.shape)
print("Type of Datatype : ",npl.dtype)

#Arthimetic Operations
print("Addition       : ",npl+10)
print("Multiplication : ",npl*10)
print("Subtraction    : ",npl-10)
print("Division       : ",npl/10)
print()

# 2 Dimensional Array
c = np.array([(1,2,3),(4,5,6)])
print("2 Dimensional Array : \n",c)
print("Matrix : ",c.shape)
print()

# 3 Dimensional Array
d = np.array([(1,2,3),(4,5,6),(7,8,9),(10,11,12)])
print("3 Dimensional Array : \n",d)
print("Matrix : ",d.shape)
print()
print("Reshape into (3,4) : \n",d.reshape(3,4))
print()

# Horizontal Stack
f = np.array([1,2,3])
g = np.array([4,5,6])
print("Horizontal Stack :\n",np.hstack(f))
print()

# Vertical Stack
print("Vertical Stack :\n",np.vstack(g))
print()

# Random
normal_array = np.random.normal(5,0.5,10)
print("Random :\n",normal_array)
print("Min : ",np.min(normal_array))
print("Max : ",np.max(normal_array))
print("Median : ",np.median(normal_array))
print("std : ",np.std(normal_array))
print()

# Arrange
print("Arrange :")
print(np.arange(1,11))
print(np.arange(1,14,4))
print()

# Slicing
e = np.array([[1,2,3],[4,5,6]])
print("Array :\n",e)
print("\nPrinting 0th Index Element :\n",e[0])
print("\nPrinting 1st Index Element :\n",e[1])



#Practical 8 (Compute a program in python using Pandas usage.)
import pandas as pd
S = pd.Series([11, 28, 72, 3, 5, 8])
S
print(S.index)
print(S.values)
print("\n")

#defining Series objects with individual indices:
fruits = ['apples', 'oranges', 'cherries', 'pears']
quantities = [20, 33, 52, 10]
fruitdetails = pd.Series(quantities, index=fruits)
print(fruitdetails)
print("\n")

#Creating Series Objects from Dictionaries
cities = {"London":    12000,
          "Berlin":    14000,
          "Madrid":    45000,
          "Rome":      78050,
          "Paris":     46520,
          "Vienna":    78963,
          "Bucharest": 15302,
          "Hamburg":   78569,
          "Budapest":  25896,
          "Warsaw":    36584,
          "Barcelona": 45300,
          "Munich":    74500,
          "Milan":     62000}

city_series = pd.Series(cities)
print(city_series)
my_cities = ["London", "Paris", "Zurich", "Berlin","Stuttgart", "Hamburg"]
my_city_series = pd.Series(cities,index=my_cities)
print("\n")
print(my_city_series)
print("\n")
print(my_city_series.isnull())
print("\n")
print(my_city_series.notnull())
print("\n")

#Filtering out Missing Data
print(my_city_series.dropna())
print("\n")

#Filling in Missing Data
print(my_city_series.fillna(0))
print("\n")

#Fill some appropriate values for missng Cities
missing_cities = {"Stuttgart":50939, "Zurich":38884}
print(my_city_series.fillna(missing_cities))
print("\n")


#Since we had nan values integers are converted into float
my_city_series = my_city_series.fillna(0).astype(float)
print(my_city_series)


import pandas as pd

years = range(2014, 2018)
shop1 = pd.Series([2409.14, 2941.01, 3496.83, 3119.55], index=years)
shop2 = pd.Series([1203.45, 3441.62, 3007.83, 3619.53], index=years)
shop3 = pd.Series([3412.12, 3491.16, 3457.19, 1963.10], index=years)
shops_df = pd.concat([shop1, shop2, shop3], axis=1)
shops_df

#update column names
cities = ["Mumbai", "Pune", "Nashik"]
shops_df.columns = cities
shops_df
print("\n")

# alternative way: give names to series:
shop1.name = "Mumbai"
shop2.name = "Pune"
shop3.name = "Nashik"
print(shops_df)
print("\n")

shops_df2 = pd.concat([shop1, shop2, shop3], axis=1)
print(shops_df2)
print("\n")
print(type(shops_df))

#DataFrames from Dictionaries
cities2 = {"name": ["London", "Berlin", "Madrid", "Rome",
                   "Paris", "Vienna", "Bucharest", "Hamburg",
                   "Budapest", "Warsaw", "Barcelona",
                   "Munich", "Milan"],
          "population": [8615246, 3562166, 3165235, 2874038,
                         2273305, 1805681, 1803425, 1760433,
                         1754000, 1740119, 1602386, 1493900,
                         1350680],
          "country": ["England", "Germany", "Spain", "Italy",
                      "France", "Austria", "Romania",
                      "Germany", "Hungary", "Poland", "Spain",
                      "Germany", "Italy"]}

city_frame = pd.DataFrame(cities2)
city_frame

#Retrieving the Column Names
city_frame.columns.values

#Providing custom index
ordinals = ["first", "second", "third", "fourth",
            "fifth", "sixth", "seventh", "eigth",
            "ninth", "tenth", "eleventh", "twelvth",
            "thirteenth"]
city_frame = pd.DataFrame(cities2, index=ordinals)
city_frame

#Rearranging the Order of Columns
city_frame = pd.DataFrame(cities2,columns=["name","country","population"])
city_frame

#making Existing Column as the Index of a DataFrame
city_frame = pd.DataFrame(cities2,columns=["name", "population"],index=cities2["country"])
city_frame

#Accessing Rows via Index Values
city_frame = pd.DataFrame(cities2,columns=("name", "population"),index=cities2["country"])
print(city_frame.loc["Germany"])

#extracting rows by chosen more than on index labels
print(city_frame.loc[["Germany", "France"]])

#select pandas DataFrame rows based on conditions
condition = city_frame.population>2000000
condition
print(city_frame.loc[condition])
condition1 = (city_frame.population>1500000)
condition2 = (city_frame['name'].str.contains("m"))
print(city_frame.loc[condition1 & condition2])

#Adding Rows to a DataFrame
milan = ['Milan', 1399860]
city_frame.iloc[-1] = milan
city_frame.loc['Switzerland'] = ['Zurich', 415215]
city_frame


#Practical 9 (Implement the PCA using Python.)

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
Cancer = load_breast_cancer()
Cancer.keys()
#print(Cancer['DESCR'])
df = pd.DataFrame(Cancer['data'],columns=Cancer['feature_names'])
print(df)
from sklearn.preprocessing import StandardScaler
Scaler = StandardScaler()
Scaler.fit(df)
Scaled_data = Scaler.transform(df)
print(Scaled_data)
from sklearn.decomposition import PCA
pca = PCA(n_components=3)
pca.fit(Scaled_data)
x_pca=pca.transform(Scaled_data)
x_pca.shape
print(x_pca)

#2D
plt.figure(figsize=(8,6))
plt.scatter(x_pca[:,0],x_pca[:,1])
c=Cancer['target']
plt.xlabel("1st Principle Component")
plt.ylabel("2nd Principle Component")

#3D
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure(figsize=(10,10))
axis = fig.add_subplot(111,projection='3d')
axis.scatter(x_pca[:,0],x_pca[:,1],x_pca[:,2],c=Cancer['target'],cmap='plasma')
axis.set_xlabel("1st PC",fontsize=10)
axis.set_ylabel("2st PC",fontsize=10)
axis.set_zlabel("3st PC",fontsize=10)

#Check Variance Ratio
print(pca.explained_variance_ratio_)


#Practical 10 (Consider a set of data points and train your model in python. The model should have 80% training data and 20% of test data.)

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
iris_data = load_iris()
iris_data
iris_data.keys()
df = pd.DataFrame(iris_data.data, columns = iris_data.feature_names)
df
training_data, testing_data = train_test_split(df, test_size=0.2)
print(training_data)
print(testing_data)
print(f"No. of training examples : {training_data.shape[0]}")
print(f"No. of testing examples : {testing_data.shape[0]}")
training_data.head()



#Practical 11 (Implement the Regression algorithm: Linear Regression in python.)
from google.colab import files
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
#df = files.upload()
df = pd.read_csv('Salary_Data.csv')
df
x = df.iloc[:,0].values  #input
y = df.iloc[:,1].values  #output
print(x.shape)
print(y.shape)
x = x.reshape(-1,1)
y = y.reshape(-1,1)
print(x.shape)
print(y.shape)
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2,random_state = 0)
print("x Training:",x_train)
print(x_train.shape)
print("\nx Testing:",x_test)
print(x_test.shape)
print("y Training:",y_train)
print(y_train.shape)
print("\ny Testing:",y_test)
print(y_test.shape)
plt.scatter(x_train,y_train,color = 'r',marker = '+')
plt.xlabel("Years Experience")
plt.ylabel('Salary')
plt.title('Employee Details')
plt.show()
from sklearn.linear_model import LinearRegression
reg = LinearRegression()
reg.fit(x_train,y_train)
reg.coef_
reg.intercept_
y_pred = reg.predict(x_test)
print(y_pred)
print(y_test)
print(y_pred)
print(y_test)
plt.scatter(x_train,y_train,color = 'r',marker = '+')
plt.xlabel("Years Experience")
plt.ylabel('Salary')
plt.plot(x_train,reg.predict(x_train))
plt.title('Employee Details')
plt.show()



import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.model_selection import train_test_split
boston = datasets.load_boston()
x = boston.data
y = boston.target
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.4,random_state = 0)
reg = linear_model.LinearRegression()
reg.fit(x_train, y_train)
print("Coefficient : ",reg.coef_)
print("Variance Score :",format(reg.score(x_test,y_test)))


plt.scatter(reg.predict(x_train),reg.predict(x_train) - y_train, color = "red", s =10, label = 'train data')
plt.scatter(reg.predict(x_test),reg.predict(x_test) - y_test, color = "green", s =10, label = 'test data')
plt.hlines(y = 0,xmin = 0,xmax = 50, linewidth = 2)
plt.legend(loc = 'upper right')
plt.title('Residual Errors')
plt.show()