We Keep Coding

How to predict an individual value using SKlearn?

I am very new to Machine Learning and I would like to get a percentage returned for an individual array that I pass in the prediction model I have created.
I'm not sure how to go about getting the match percentage. I thought it was metrics.accuracy_score(Ytest, y_pred) but when I try that it gives me the following error:
**ValueError: Found input variables with inconsistent numbers of samples: [4, 1]**
I have no idea if this is the correct way to go about this.
import numpy as np #linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt #For Visualisation
import seaborn as sns #For better Visualisation
from bs4 import BeautifulSoup #For Text Parsing
import mysql.connector
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import joblib
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import GaussianNB
import docx2txt
import re
import csv
from sklearn import metrics
class Machine:
TrainData = ''
def __init__(self):
self.TrainData = self.GetTrain()
Data = self.ProcessData()
x = Data[0]
y = Data[1]
x, x_test, y, y_test = train_test_split(x,y, stratify = y, test_size = 0.25, random_state = 42)
self.Predict(x,y, '',x_test , y_test )
def Predict(self,X,Y,Data, Xtext, Ytest):
model = GaussianNB()
model.fit(Xtext, Ytest)
y_pred = model.predict([[1.0, 2.00613, 2, 5]])
print("Accuracy:",metrics.accuracy_score(Ytest, y_pred))
def ProcessData(self):
X = []
Y = []
i = 0
for I in self.TrainData:
Y.append(I[4])
X.append(I)
i = i + 1
i = 0
for j in X:
X[i][0] = float(X[i][0])
X[i][1] = float(X[i][1])
X[i][2] = int(X[i][2])
X[i][3] = int(X[i][3])
del X[i][4]
i = i + 1
return X,Y
def GetTrain(self):
file = open('docs/training/TI_Training.csv')
csvreader = csv.reader(file)
header = []
header = next(csvreader)
rows = []
for row in csvreader:
rows.append(row)
file.close()
return rows
Machine()

The error is pretty clear: YTest has 4 samples, and y_pred only has one. You need an equal number of samples in each to get any metrics. I suspect you instead want to do
y_pred = model.predict(Xtext)
in your Predict function.

np.expm1 doesn't return desired value

I'm currently trying the following concept:
I applied ‍np.log1p() to the independent variables and dependent variable (price)
Assuming X = independent variables and Y = dependent variable, I train_test_split X & Y
Then I trained the LinearRegression(), Ridge(), Lasso(), and ElasticNet() models
Given that the labels I used to train the model were also log1p(Y), I'm assuming the model predictions are also log values?
If the predictions are log values, how come np.expm1 doesn't return a value that is on a similar scale?
Linear Regression Code for reference
import os
import glob
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import re
from scipy.stats import skew
from scipy import stats
from scipy.stats import norm
from sklearn.model_selection import cross_val_score, train_test_split, GridSearchCV, ShuffleSplit
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
df_num = pd.DataFrame(np.random.randint(0,100,size=(10000, 4)), columns=list('ABCD'))
df_cat = pd.DataFrame(np.random.randint(0,2,size=(10000, 2)), columns=['cat1', 'cat2'])
price = pd.DataFrame(np.random.randint(0,100,size=(10000, 1)), columns=['price'])
y = price
skewness = df_num.apply(lambda x: skew(x))
skewness = skewness[abs(skewness) > 0.5]
skewed_features = skewness.index
df_num[skewed_features] = np.log1p(df_num[skewed_features])
y = np.log1p(y)
train = pd.concat([df_num, df_cat], axis = 1)
X_train, X_test, y_train, y_test = train_test_split(train, y, test_size = 0.3, random_state = 0)
lr_clf = LinearRegression()
lr_clf.fit(X_train, y_train)
def predict_price(A, B, C, D, cat1):
cat1_index = np.where(train.columns == cat1)[0][0]
x = np.zeros(len(train.columns))
x[0] = np.log1p(A)
x[1] = np.log1p(B)
x[2] = np.log1p(C)
x[3] = np.log1p(D)
if cat1_index >= 0:
x[cat1_index] = 1
return np.expm1(lr_clf.predict([x])[0])
predict_price(20, 30, 15, 55, 'cat2')
EDIT1: I tried to recreate an example from scratch, but I can't seem to replicate the issue I'm running into. The issue I run into in my real data is that:
predictions work totally fine if I DON'T log-normalize inputs when training and DON'T log normalize inputs when predicting.
HOWEVER when I do log-normalize when training and log normalize inputs and np.expm1 the prediction, the value is totally off.
Please let me know if there is anything I can explain more clearly.

Complement Naive Bayes and weighted class in sklearn

I'm trying to implement a complement naive bayes classifier using sklearn. My data have very imbalanced classes (30k samples of class 0 and 6k samples of the 1 class) and I'm trying to compensate this using weighted class.
Here is the shape of my dataset:
enter image description here
I tried to use the compute compute_class_weight function to calcute the weights and then pass it to the fit function when training my model:
import numpy as np
import seaborn as sn
import pandas as pd
from pandas import DataFrame
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.utils import class_weight
from sklearn.naive_bayes import ComplementNB
#Import the csv data
data = pd.read_csv('output_pt900.csv')
#Create the header of the csv file
header = []
for x in range(0,2500):
header.append('pixel' + str(x))
header.append('status')
#Add the header to the csv data
data.columns = header
#Replace the b's and the f's in the status column by 0 and 1
data['status'] = data['status'].replace('b',0)
data['status'] = data['status'].replace('f',1)
print(data)
#Drop the NaN values
data = data.dropna()
#Separate the features variables and the status
y = data['status']
x = data.drop('status',axis=1)
#Split the original dataset into two other: train and test
x_train, x_test, y_train, y_test = train_test_split(x,y, test_size = 0.2)
all_together = y_train.to_numpy()
unique_classes = np.unique(all_together)
c_w = class_weight.compute_class_weight('balanced', unique_classes, all_together)
clf = ComplementNB()
clf.fit(x_train,y_train, c_w)
y_predict = clf.predict(x_test)
cm = confusion_matrix(y_test, y_predict)
svm = sn.heatmap(cm, cmap='Blues', annot=True, fmt='g')
figure=svm.get_figure()
figure.savefig('confusion_matrix_cnb.png', dpi=400)
plt.show()
but I got thesse error:
ValueError: sample_weight.shape == (2,), expected (29752,)!
Anyone knows how to use weighted class in sklearn models?

compute_class_weight returns an array of length equal to the number of unique classes with the weight to assign to instances of each class (link). So if there are 2 unique classes, c_w has length 2, containing the weight that should be assigned to samples with label 0 and 1.
When calling fit for your model, the weight for each sample is expected by the sample_weight argument. This should explain the error you received. To solve this issue, you need to use c_w returned by compute_class_weight to create an array of individual sample weights. You could do this with [c_w[i] for i in all_together]. Your fit call would ultimately look something like:
clf.fit(x_train, y_train, sample_weight=[c_w[i] for i in all_together])

how to convert pd.DataFrame to tf.data.Dataset (or use insted pd.DataFrame) for DNNClassifier

I am having this warning.
Instructions for updating:
To construct input pipelines, use the tf.data module.
I have had some search but I couldn't figure out the logic behind the tf.data.Dataset, so I couldn't manage converting pd.DataFrame into tf.data.Dataset.
I also need help for predictions at the end of the code, I couldn't figure out right way to compare predictions(high probability output) with label.
Note: data has no column names, so I have added a1 to a784 names to columns so I can assign them to feature_columns.
Thanks is advance.
Here is the code:
import numpy as np
import pandas as pd
import seaborn as sns
import tensorflow as tf
from sklearn import metrics
from tensorflow.python.data import Dataset
mnist_df = pd.read_csv("https://download.mlcc.google.com/mledu-datasets/mnist_train_small.csv",header=None)
mnist_df.describe()
mnist_df.columns
hand_df = mnist_df[0]
matrix_df = mnist_df.drop([0],axis=1)
matrix_df.head()
hand_df.head()
#creating cols array and append a1 to a784 in order to name columns
cols=[]
for i in range(785):
if i!=0:
a = '{}{}'.format('a',i)
cols.append(a)
matrix_df.columns = cols
mnist_df = mnist_df.head(10000)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(matrix_df, hand_df, test_size=0.3, random_state=101)
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
matrix_df = pd.DataFrame(data=scaler.fit_transform(matrix_df),
columns=matrix_df.columns,
index=matrix_df.index)
#naming columns so I will not get error while assigning feature_columns
for i in range(len(cols)):
a=i+1
b='{}{}'.format('a',a)
cols[i] = tf.feature_column.numeric_column(str(b))
matrix_df.head()
input_func = tf.estimator.inputs.pandas_input_fn(x=X_train,y=y_train,
batch_size=10,num_epochs=1000,
shuffle=True)
my_optimizer = tf.train.AdagradOptimizer(learning_rate=0.03)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
model = tf.estimator.DNNClassifier(feature_columns=cols,
hidden_units=[32,64],
n_classes=10,
optimizer=my_optimizer,
config=tf.estimator.RunConfig(keep_checkpoint_max=1))
model.train(input_fn=input_func,steps=1000)
predict_input_func = tf.estimator.inputs.pandas_input_fn(x=X_test,
batch_size=50,
num_epochs=1,
shuffle=False)
pred_gen = model.predict(predict_input_func)
predictions = list(pred_gen)
predictions[0]

How to increase the model accuracy of multiple linear regression

This is the custom code
#Custom model for multiple linear regression
import numpy as np
import pandas as pd
dataset = pd.read_csv("50s.csv")
x = dataset.iloc[:,:-1].values
y = dataset.iloc[:,4:5].values
from sklearn.preprocessing import LabelEncoder
lb = LabelEncoder()
x[:,3] = lb.fit_transform(x[:,3])
from sklearn.preprocessing import OneHotEncoder
on = OneHotEncoder(categorical_features=[3])
x = on.fit_transform(x).toarray()
x = x[:,1:]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=1/5, random_state=0)
con = np.matrix(X_train)
z = np.matrix(y_train)
#training model
result1 = con.transpose()*con
result1 = np.linalg.inv(result1)
p = con.transpose()*z
f = result1*p
l = []
for i in range(len(X_test)):
temp = f[0]*X_test[i][0] + f[1]*X_test[i][1] +f[2]*X_test[i][2]+f[3]*X_test[i][3]+f[4]*X_test[i][4]
l.append(temp)
import matplotlib.pyplot as plt
plt.scatter(y_test,l)
plt.show()
Then I created created a model with scikit learn
and compared the results with y_test and l(predicted values of above code)
comparisons are as follows
for i in range(len(prediction)):
print(y_test[i],prediction[i],l[i],sep=' ')
103282.38 103015.20159795816 [[116862.44205399]]
144259.4 132582.27760816005 [[118661.40080974]]
146121.95 132447.73845175043 [[124952.97891882]]
77798.83 71976.09851258533 [[60680.01036438]]
This were the comparison between y_test,scikit-learn model predictions and custom code predictions
please help with the accuracy of model.
blue :Custom model predictions
yellow : scikit-learn model predictions