Develop Reference

How to merge predicted values to original pandas test data frame where X_test has been converted using CountVectorizer before splitting

I want to merge my predicted results of my test data to my X_test. I was able to merge it with y_test but since my X_test is a corpus I'm not sure how I can identify the indexes to merge.
My codes are as below
def lr_model(df):
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import pandas as pd
# Create corpus as a list
corpus = df['text'].tolist()
cv = CountVectorizer()
X = cv.fit_transform(corpus).toarray()
y = df.iloc[:, -1].values
# Splitting to testing and training
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
# Train Logistic Regression on Training set
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Merge true vs predicted labels
true_vs_pred = pd.DataFrame(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))
return true_vs_pred
This gives me the y_test and y_pred but I'm not sure how I can add the X_test as an original data frame (the ids of the X_test) to this.
Any guidance is much appreciated. Thanks

Using a pipeline can help you link the original X_test with the prediction:
def lr_model(df):
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import pandas as pd
from sklearn.pipeline import Pipeline
# Defining X and y
cv = CountVectorizer()
X = df['text']
y = df.iloc[:, -1].values
# Splitting to testing and training
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
# Create a pipeline
pipeline = Pipeline([
('CountVectorizer', cv),
('LogisticRegression', LogisticRegression(random_state = 0)),
])
# Train pipeline on Training set
pipeline.fit(X_train, y_train)
# Predicting the Test set results
y_pred = pipeline.predict(X_test)
return X_test, y_test, y_pred

How to evaluate the effect of different methods of handling missing values?

I am a total beginner and I am trying to compare different methods of handling missing data. In order to evaluate the effect of each method (drop raws with missing values, drop columns with missigness over 40%, impute with the mean, impute with the KNN), I compare the results of the LDA accuracy and LogReg accuracy on the training set between a dataset with 10% missing values, 20% missing values against the results of the original complete dataset. Unfortunately, I get pretty much the same results even between the complete dataset and the dataset with 20% missing-ness. I don't know what I am doing wrong.
from numpy import nan
from numpy import isnan
from pandas import read_csv
from sklearn.impute import SimpleImputer
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
#dataset = read_csv('telecom_churn_rev10.csv')
dataset = read_csv('telecom_churn_rev20.csv')
dataset = dataset.replace(nan, 0)
values = dataset.values
X = values[:,1:11]
y = values[:,0]
dataset.fillna(dataset.mean(), inplace=True)
#dataset.fillna(dataset.mode(), inplace=True)
print(dataset.isnull().sum())
imputer = SimpleImputer(missing_values = nan, strategy = 'mean')
transformed_values = imputer.fit_transform(X)
print('Missing: %d' % isnan(transformed_values).sum())
model = LinearDiscriminantAnalysis()
cv = KFold(n_splits = 3, shuffle = True, random_state = 1)
result = cross_val_score(model, X, y, cv = cv, scoring = 'accuracy')
print('Accuracy: %.3f' % result.mean())
#print('Accuracy: %.3f' % result.mode())
print(dataset.describe())
print(dataset.head(20))
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test,y_pred)
from sklearn import metrics
# make predictions on X
expected = y
predicted = classifier.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))
# make predictions on X test
expected = y_test
predicted = classifier.predict(X_test)
# summarize the fit of the model
print(metrics.confusion_matrix(expected, predicted))
print(metrics.classification_report(expected, predicted))

You replace all your missing values with 0 at that line : dataset = dataset.replace(nan, 0). After this line, you have a full dataset without missing values. So, the .fillna() and the SimpleImputer() are useless after that line.

I am trying to make Simple Linear Regression Model with the salary data csv file , and there are 35 data points . how do i split it in 80-20?

# split train test data
from sklearn.model_selection import train_test_split
X_train, y_train, X_test, y_test = train_test_split(x, y, test_size=0.2, random_state=1)
# import required modules and train the ML algorithm
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
i am getting the error-
Found input variables with inconsistent numbers of samples: [28, 7]

By salary csv data, i will take this one as example
https://www.kaggle.com/karthickveerakumar/salary-data-simple-linear-regression
from sklearn.model_selection import train_test_split
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
#Import the dataset
salary_data=pd.read_csv("/mnt/c/Users/XXXXXXX/Downloads/Salary_Data.csv")
# Here you can split your dataset between train and test using 80% for train
X_train, X_test, y_train, y_test = train_test_split(salary_data["YearsExperience"], salary_data["Salary"], test_size=0.2, random_state=1)
#Then you can fit your linear model on train dataset
#Here the goal is to modelize salary considering years of XP
regressor = LinearRegression()
model = regressor.fit(X_train.values.reshape(-1, 1),y_train.values.reshape(-1, 1))
#Let's plot our model prediction on whole data and compare to real data
plt.title("Salary/Years of XP")
plt.ylabel("Salary $")
plt.xlabel("Years")
plt.plot(salary_data["YearsExperience"],salary_data["Salary"],color="blue",label="real data")
plt.plot(salary_data["YearsExperience"],model.predict(salary_data["YearsExperience"].values.reshape(-1,1)),color="red",label="linear model")
plt.legend()
plt.show()

Trying to implement XGBoost into my Artificial Neural Network

I'm completely unaware as to why i'm receiving this error. I am trying to implement XGBoost but it returns with error "ValueError: For a sparse output, all columns should be a numeric or convertible to a numeric." Even after i've One Hot Encoded my categorical data. If anyone knows what is causing this and a possible solution i'd greatly appreciate it. Here is my code written in Python:
# Artificial Neural Networks - With XGBoost
# PRE PROCESS
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
# Encoding Categorical Data
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer([('encoder', OneHotEncoder(), [1, 2])],
remainder = 'passthrough')
X = np.array(ct.fit_transform(X), dtype = np.float)
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)
# Fitting XGBoost to the training set
from xgboost import XGBClassifier
classifier = XGBClassifier()
classifier.fit(x_train, y_train)
# Predicting the Test set Results
y_pred = classifier.predict(x_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
# Applying k-Fold Cross Validation
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10)
accuracies.mean()
accuracies.std()

added Standardscaler but receive errors in Cross Validation and the correlation matrix

This is the code I built to apply a multiple linear regression. I added standard scaler to fix the Y intercept p-value which was not significant but the problem that the results of CV RMSE in the end changed and have nosense anymore and received an error in the code for plotting the correlation Matrix saying : AttributeError: 'numpy.ndarray' object has no attribute 'corr'
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm
from scipy import stats
from scipy.stats.stats import pearsonr
# Import Excel File
data = pd.read_excel("C:\\Users\\AchourAh\\Desktop\\Multiple_Linear_Regression\\SP Level Reasons Excels\\SP000273701_PL14_IPC_03_09_2018_Reasons.xlsx",'Sheet1') #Import Excel file
# Replace null values of the whole dataset with 0
data1 = data.fillna(0)
print(data1)
# Extraction of the independent and dependent variables
X = data1.iloc[0:len(data1),[1,2,3,4,5,6,7]] #Extract the column of the COPCOR SP we are going to check its impact
Y = data1.iloc[0:len(data1),9] #Extract the column of the PAUS SP
# Data Splitting to train and test set
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size =0.25,random_state=1)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)
# Statistical Analysis of the training set with Statsmodels
X = sm.add_constant(X_train) # add a constant to the model
est = sm.OLS(Y_train, X).fit()
print(est.summary()) # print the results
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import math
lm = LinearRegression() # create an lm object of LinearRegression Class
lm.fit(X_train,Y_train) # train our LinearRegression model using the training set of data - dependent and independent variables as parameters. Teaching lm that Y_train values are all corresponding to X_train.
print(lm.intercept_)
print(lm.coef_)
mse_test = mean_squared_error(Y_test, lm.predict(X_test))
print(math.sqrt(mse_test))
# Data Splitting to train and test set of the reduced data
X_1 = data1.iloc[0:len(data1),[1,2]] #Extract the column of the COPCOR SP we are going to check its impact
X_train2, X_test2, Y_train2, Y_test2 = train_test_split(X_1, Y, test_size =0.25,random_state=1)
X_train2 = ss.fit_transform(X_train2)
X_test2 = ss.transform(X_test2)
# Statistical Analysis of the reduced model with Statsmodels
X_reduced = sm.add_constant(X_train2) # add a constant to the model
est_reduced = sm.OLS(Y_train2, X_reduced).fit()
print(est_reduced.summary()) # print the results
# Fitting a Linear Model for the reduced model with Scikit-Learn
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import math
lm1 = LinearRegression() #create an lm object of LinearRegression Class
lm1.fit(X_train2, Y_train2)
print(lm1.intercept_)
print(lm1.coef_)
mse_test1 = mean_squared_error(Y_test2, lm1.predict(X_test2))
print(math.sqrt(mse_test1))
#Cross Validation and Training again the model
from sklearn.model_selection import KFold
from sklearn import model_selection
kf = KFold(n_splits=6, random_state=1)
for train_index, test_index in kf.split(X_train2):
print("Train:", train_index, "Validation:",test_index)
X_train1, X_test1 = X[train_index], X[test_index]
Y_train1, Y_test1 = Y[train_index], Y[test_index]
results = -1 * model_selection.cross_val_score(lm1, X_train1, Y_train1,scoring='neg_mean_squared_error', cv=kf)
print(np.sqrt(results))
#RMSE values interpretation
print(math.sqrt(mse_test1))
print(math.sqrt(results.mean()))
#Good model built no overfitting or underfitting (Barely Same for test and training :Goal of Cross validation but low prediction accuracy = Value is big
import seaborn
Corr=X_train2.corr(method='pearson')
mask=np.zeros_like(Corr)
mask[np.triu_indices_from(mask)]=True
seaborn.heatmap(Corr,cmap='RdYlGn_r',vmax=1.0,vmin=-1.0,mask=mask, linewidths=2.5)
plt.yticks(rotation=0)
plt.xticks(rotation=90)
plt.show()
enter code here
Do you have an idea how to fix the issue ?

I'm guessing the problem lies with:
Corr=X_train2.corr(method='pearson')
.corr is a pandas dataframe method but X_train2 is a numpy array at that stage. If a dataframe/series is passed into StandardScaler, a numpy array is returned. Try replacing the above with:
Corr=pd.DataFrame(X_train2).corr(method='pearson')
or make use of numpy.corrcoef or numpy.correlate in their respective forms.