Skip to content

Instantly share code, notes, and snippets.

View kushalvala's full-sized avatar
🌎
Working from home

Kushal kushalvala

🌎
Working from home
View GitHub Profile
@kushalvala
kushalvala / fastapi_imdb.py
Created April 2, 2021 16:35
FastAPI Python File
import uvicorn
from typing import List
from pydantic import BaseModel
from fastapi import FastAPI
import tensorflow as tf
app = FastAPI()
model = tf.keras.models.load_model('../model/tf_keras_imdb')
class Reviews(BaseModel):
import pandas as pd
data = pd.read_csv('winequality-red.csv', sep = ';')
data.head()
# Output:
fixed acidity volatile acidity citric acid residual sugar chlorides free sulfur dioxide total sulfur dioxide density pH sulphates alcohol quality
0 7.4 0.70 0.00 1.9 0.076 11.0 34.0 0.9978 3.51 0.56 9.4 5
1 7.8 0.88 0.00 2.6 0.098 25.0 67.0 0.9968 3.20 0.68 9.8 5
2 7.8 0.76 0.04 2.3 0.092 15.0 54.0 0.9970 3.26 0.65 9.8 5
3 11.2 0.28 0.56 1.9 0.075 17.0 60.0 0.9980 3.16 0.58 9.8 6
def generate_co_occurrence_matrix(corpus):
vocab = set(corpus)
vocab = list(vocab)
vocab_index = {word: i for i, word in enumerate(vocab)}
# Create bigrams from all words in corpus
bi_grams = list(bigrams(corpus))
# Frequency distribution of bigrams ((word1, word2), num_occurrences)
# Importing the library
from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd
import numpy as np
# Text Corpus
corpus = ['This movie is very Scary and long',
'This movie is not scary and is slow',
'This movie is spooky and good'
]
from sklearn.feature_extraction.text import CountVectorizer
corpus = ['This movie is very Scary and long',
'This movie is not scary and is slow',
'This movie is spooky and good'
]
# Defining the method to generate 1-gram BoW Tokens
vectorizer = CountVectorizer(lowercase = True, ngram_range = (1,1))