MLWhiz

# Generate a proposal cipher by swapping letters at two random location
def generate_cipher(cipher):
    pos1 = random.randint(0, len(list(cipher))-1)
    pos2 = random.randint(0, len(list(cipher))-1)
    if pos1 == pos2:
        return generate_cipher(cipher)
    else:
        cipher = list(cipher)
        pos1_alpha = cipher[pos1]
        pos2_alpha = cipher[pos2]

MLWhiz

# Takes as input a text to decrypt and runs a MCMC algorithm for n_iter. Returns the state having maximum score and also
# the last few states 
def MCMC_decrypt(n_iter,cipher_text,scoring_params):
    current_cipher = string.ascii_uppercase # Generate a random cipher to start
    state_keeper = set()
    best_state = ''
    score = 0
    for i in range(n_iter):
        state_keeper.add(current_cipher)
        proposed_cipher = generate_cipher(current_cipher)

MLWhiz

## Run the Main Program:

scoring_params = create_scoring_params_dict('war_and_peace.txt')

plain_text = "As Oliver gave this first proof of the free and proper action of his lungs, \
the patchwork coverlet which was carelessly flung over the iron bedstead, rustled; \
the pale face of a young woman was raised feebly from the pillow; and a faint voice imperfectly \
articulated the words, Let me see the child, and die. \
The surgeon had been sitting with his face turned towards the fire: giving the palms of his hands a warm \
and a rub alternately. As the young woman spoke, he rose, and advancing to the bed's head, said, with more kindness \

MLWhiz

import numpy as np

W = [20,40,60,12,34,45,67,33,23,12,34,56,23,56]
G = [120,420,610,112,341,435,657,363,273,812,534,356,223,516]
W_max = 150

# This function takes a state X , The gold vector G and a Beta Value and return the Log of score
def score_state_log(X,G,Beta):
    return Beta*np.dot(X,G)

MLWhiz

# Takes as input a text to decrypt and runs a MCMC algorithm for n_iter. Returns the state having maximum score and also
# the last few states 
def MCMC_Golddigger(n_iter,W,G,W_max, Beta_start = 0.05, Beta_increments=.02):
    M = len(W)
    Beta = Beta_start
    current_X = [0]*M # We start with all 0's
    state_keeper = []
    best_state = ''
    score = 0
    

MLWhiz

max_state_value =0 
Solution_MCMC = [0]
for i in range(10):
    state_keeper,best_state = MCMC_Golddigger(50000,W,G,W_max,0.0005, .0005)
    state_value=np.dot(best_state,G)
    if state_value>max_state_value:
        max_state_value = state_value
        Solution_MCMC = best_state

print("MCMC Solution is :" , str(Solution_MCMC) , "with Gold Value:", str(max_state_value))

MLWhiz

{
    "snippets" : [
        {
            "name" : "example",
            "code" : [
                "# This is an example snippet!",
                "# To create your own, add a new snippet block to the",
                "# snippets.json file in your jupyter nbextensions directory:",
                "# /nbextensions/snippets/snippets.json",
                "import this"

MLWhiz

# Create a RDD from RatingRDD that only contains the two columns of interest i.e. movie_id,rating.
RDD_movid_rating = ratingRDD.map(lambda x : (x.split("\t")[1],x.split("\t")[2]))
print("RDD_movid_rating:",RDD_movid_rating.take(4))

# Create a RDD from MovieRDD that only contains the two columns of interest i.e. movie_id,title.
RDD_movid_title = movieRDD.map(lambda x : (x.split("|")[0],x.split("|")[1]))
print("RDD_movid_title:",RDD_movid_title.take(2))

# merge these two pair RDDs based on movie_id. For this we will use the transformation leftOuterJoin(). See the transformation document.
rdd_movid_title_rating = RDD_movid_rating.leftOuterJoin(RDD_movid_title)

MLWhiz

# Create a RDD from RatingRDD that only contains the two columns of interest i.e. movie_id,rating.
RDD_movid_rating = ratingRDD.map(lambda x : (x.split("\t")[1],x.split("\t")[2]))
print("RDD_movid_rating:",RDD_movid_rating.take(4))

# Create a RDD from MovieRDD that only contains the two columns of interest i.e. movie_id,title.
RDD_movid_title = movieRDD.map(lambda x : (x.split("|")[0],x.split("|")[1]))
print("RDD_movid_title:",RDD_movid_title.take(2))

# merge these two pair RDDs based on movie_id. For this we will use the transformation leftOuterJoin(). See the transformation document.
rdd_movid_title_rating = RDD_movid_rating.leftOuterJoin(RDD_movid_title)

MLWhiz

print(((ratingRDD.map(lambda x : (x.split("\t")[1],x.split("\t")[2]))).
     leftOuterJoin(movieRDD.map(lambda x : (x.split("|")[0],x.split("|")[1])))).
     map(lambda x: (x[1][1],1)).
     reduceByKey(lambda x,y: x+y).
     takeOrdered(25,lambda x:-x[1]))