isauravmanitripathi

from positional_encoding import PositionEmbeddingFixedWeights

class Decoder(Layer):
    def __init__(self, vocab_size, sequence_length, h, d_k, d_v, d_model, d_ff, n, rate, **kwargs):
        super(Decoder, self).__init__(**kwargs)
        self.pos_encoding = PositionEmbeddingFixedWeights(sequence_length, vocab_size, d_model)
        self.dropout = Dropout(rate)
        self.decoder_layer = [DecoderLayer(h, d_k, d_v, d_model, d_ff, rate) for _ in range(n)
        ...

isauravmanitripathi

...
def call(self, x, encoder_output, lookahead_mask, padding_mask, training):
    # Multi-head attention layer
    multihead_output1 = self.multihead_attention1(x, x, x, lookahead_mask)
    # Expected output shape = (batch_size, sequence_length, d_model)

    # Add in a dropout layer
    multihead_output1 = self.dropout1(multihead_output1, training=training)

    # Followed by an Add & Norm layer

isauravmanitripathi

from multihead_attention import MultiHeadAttention
from encoder import AddNormalization, FeedForward

class DecoderLayer(Layer):
    def __init__(self, h, d_k, d_v, d_model, d_ff, rate, **kwargs):
        super(DecoderLayer, self).__init__(**kwargs)
        self.multihead_attention1 = MultiHeadAttention(h, d_k, d_v, d_model)
        self.dropout1 = Dropout(rate)
        self.add_norm1 = AddNormalization()
        self.multihead_attention2 = MultiHeadAttention(h, d_k, d_v, d_model)

isauravmanitripathi

#preprocessing 
#remove missing values 
loans = loans.dropna() 
#remove outliers 
q_low = loans["annual_inc"].quantile(0.08) 
q_hi = loans["annual_inc"].quantile(0.92) loans = loans[(loans["annual_inc"] < q_hi) & (loans["annual_inc"] > q_low)] 
loans = loans[(loans['dti'] <=45)] 
q_hi = loans['bc_open_to_buy'].quantile(0.95) 
loans = loans[(loans['bc_open_to_buy'] < q_hi)] 
loans = loans[(loans['bc_util'] <=160)] 

isauravmanitripathi

# PROCESSING & DISPLAY
def display():
    with st.container():
        st.write("#### Which cities and states have recorded the most accidents?")
        res = computeQuery(query_8, graph)
        fig = px.treemap(res, path=[px.Constant("U.S"), "state", "city"], values="count", hover_data=["state", "city","count"],
                color="count",
                color_continuous_scale='tealrose',
                color_continuous_midpoint=np.average(res['count'], weights=res['count']))
        st.plotly_chart(fig, use_container_width=True)

isauravmanitripathi

acc_category = data[["category"]]
acc_category = acc_category.drop_duplicates()
acc_category = acc_category.reset_index(drop=True)
acc_category["id"] = acc_category.index

# relate tables with index
for i, row in data.iterrows():
    cat = data.at[i, "category"]

    for j, row in acc_category.iterrows():

isauravmanitripathi

# PRELIMINARY OPERATIONS
data = pd.read_excel("./data_original.xlsx")

data = data.drop(columns=["fix_port","source", "age_youngest", "gender", "injury_desc", "report", "notes", "mechanical", "op_error", "employee"])
data = data.dropna()

data = data[data["bus_type"]=="Amusement park"]
data = data[data["industry_sector"]=="amusement ride"]
data = data[data["manufacturer"] != "In-house"]

isauravmanitripathi

nltk==3.7
pytrends==4.8.0

isauravmanitripathi

import re
from string import punctuation

import nltk
from nltk import TreebankWordTokenizer, sent_tokenize
from nltk.corpus import stopwords


class KeywordsGenerator:
    def __init__(self, pytrends):

isauravmanitripathi

import java.awt.Cursor;
import java.awt.Font;
import java.util.regex.Pattern;
import java.awt.Color;
import javax.swing.*;
import java.lang.Math;

public class calculator {

    private static final int WINDOW_WIDTH = 410;