Skip to content

Instantly share code, notes, and snippets.

Avatar
💭
For the love of data.

saimadhu saimadhu-polamuri

💭
For the love of data.
View GitHub Profile
View dataaspirant-bag-of-words-implementation.py
## dependencies
import pandas as pd
import nltk
import numpy as np
from nltk.corpus import stopwords
from nltk.tokenize import sent_tokenize as st
from nltk.stem import WordNetLemmatizer as wordnet
import re
View dataaspirant-bag-of-words-requried-pacakges.py
pip install nltk
pip install pandas
pip install numpy
## After installing the pacakges run the below code.
nltk.download()
View dataaspirant-regularization-ridge-regression-prediction.py
## Ridge Regression Predictions
final_model = Ridge(alpha=0.25)
final_model.fit(X_train, y_train)
print(final_model.score(X_test, y_test))
## Output: 0.6973569341182368
View dataaspirant-regularization-ridge-regression.py
## Ridge regression
## two lists to hold alpha values and cross-validation scores
alpha = []
ridge_scores = []
## loop over different alpha values
for i in range(1,10):
ridge_model = Ridge(alpha=0.25*i)
View dataaspirant-regularization-lasoo-regression.py
# Lasso regression
## two lists to hold alpha values and cross-validation scores
alpha = []
lasso_scores = []
## we’ll be looping over different alpha values to find the one which gives us the best score.
## loop over different alpha values
for i in range(1,10):
View dataaspirant-regularization-linear-regression-model.py
## Linear regression model
linearModel = LinearRegression()
linearModel.fit(X_train, y_train)
## Evaluating the model
print(linearModel.score(X_test, y_test))
"""
View dataaspirant-regularization-load-house-price-data.py
## import the required libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from statistics import mean
from sklearn.linear_model import LinearRegression, Ridge, Lasso
from sklearn.model_selection import train_test_split, cross_val_score
## load the dataset
df = pd.read_csv("kc_house_data.csv")
View dataaspirant-pca-visualization.py
## PCA Visualization
a_std = pca.transform(transformed)
plt.figure()
plt.title(label="PCA Visualization", fontsize=30, color="blue")
plt.xlabel("Principal Component 1")
plt.ylabel("Principal Component 2")
plt.title(label="PCA Visualization", fontsize=40, color="blue")
plt.scatter(a_std[:, 0], a_std[:, 1], c=b)
View dataaspirant-pca-create-two-pca.py
std = StandardScaler()
transformed = StandardScaler().fit_transform(a)
## Two PCA components
pca = convers_pca(no_of_components=2)
pca.fit(transformed)
print(pca.eigen_vectors)
print(pca.eigen_values)
print(pca.sorted_components)
View dataaspirant-pca-create-pca.py
class convers_pca():
def __init__(self, no_of_components):
self.no_of_components = no_of_components
self.eigen_values = None
self.eigen_vectors = None
def transform(self, a):
return np.dot(a - self.mean, self.projection_matrix.T)
You can’t perform that action at this time.