We Keep Coding

TypeError: Singleton array -1.2180335273374168 cannot be considered a valid collection

# Import libraries:
## Basic libs:
import pandas as pd
import numpy as np
import warnings
## Data Visualization:
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler # Scale Numeric Data
from sklearn.preprocessing import OneHotEncoder # Encoding Categorical Data
from sklearn.model_selection import train_test_split # Set Training and Testing Data
from sklearn import preprocessing
from sklearn import utils
from sklearn.datasets import load_iris
# Configure libraries:
warnings.filterwarnings('ignore')
plt.rcParams['figure.figsize'] = (10, 10)
plt.style.use('seaborn')
# Load dataset:
df_bank = pd.read_csv("'...'.csv")
# Drop last row by selecting all rows except last row
df_bank = df_bank.iloc[:-1 , :]
df_bank.pop('Post Message')
df_bank.pop('Posted')
# print('Shape of dataframe:', df_bank.shape)
print(df_bank.head())
# Handle missing data:
df_bank = df_bank.fillna("Unknown") # Imputation for Categorical Data
# Scale Numeric Data:
df_bank_ready = df_bank.copy() # Copying original dataframe
scaler = StandardScaler()
num_cols = ['Impressions']
df_bank_ready[num_cols] = scaler.fit_transform(df_bank[num_cols])
# Encoding Categorical Data:
encoder = OneHotEncoder(sparse=False)
cat_cols = ['Type','Weather','Weekend']
df_encoded = pd.DataFrame(encoder.fit_transform(df_bank_ready[cat_cols])) # Encode Categorical Data
df_encoded.columns = encoder.get_feature_names(cat_cols)
df_bank_ready = df_bank_ready.drop(cat_cols ,axis=1) # Replace Categotical Data with Encoded Data
df_bank_ready = pd.concat([df_encoded, df_bank_ready], axis=1)
df_bank_ready = df_bank_ready.astype(float) # Encode target value
# Split Dataset for Training and Testing:
feature = df_bank_ready.drop('Impressions', axis=1) # Select Features
print("feat:")
print(feature)
target = df_bank_ready['Impressions'] # Select Target
print("target:")
print(target)
# Set Training and Testing Data:
X_train, X_test, y_train, y_test = train_test_split(feature , target,
shuffle = True,
test_size=0.2,
random_state=1)
# Modelling:
def evaluate_model(model, x_test, y_test):
from sklearn import metrics
# Predict Test Data:
y_pred = model.predict(x_test)
# convert the continuous values of the response variable to categorical value:
lab = preprocessing.LabelEncoder()
y_pred = lab.fit_transform(y_pred)
y_test = lab.fit_transform(y_test)
prec = metrics.precision_score(y_test, y_pred,
pos_label='positive',
average='micro')
# rec = metrics.recall_score(y_test, y_pred)
rec = metrics.recall_score(y_test, y_pred,
average='micro',
pos_label='positive')
f1 = metrics.f1_score(y_test, y_pred,
average='micro',
pos_label='positive')
kappa = metrics.cohen_kappa_score(y_test, y_pred)
# Calculate area under curve (AUC):
y_pred_proba = model.predict(x_test)[1]
fpr, tpr, _ = metrics.roc_curve(y_test, y_pred_proba,
pos_label='positive')
auc = metrics.roc_auc_score(y_test, y_pred_proba)
# Display confussion matrix:
cm = metrics.confusion_matrix(y_test, y_pred)
return {
# 'acc': acc,
'prec': prec, 'rec': rec
#, 'f1': f1, 'kappa': kappa,'fpr': fpr, 'tpr': tpr, 'auc': auc, 'cm': cm
}
# Building Model:
from sklearn import tree
from sklearn.tree import DecisionTreeRegressor
# Building Decision Tree model:
dtc = DecisionTreeRegressor(random_state=0)
dtc.fit(X_train, y_train)
# Evaluate Model:
dtc_eval = evaluate_model(dtc, X_test, y_test)
# Print result:
print('Precision:', dtc_eval['prec'])
print('Recall:', dtc_eval['rec'])
Trying to build a supervised machine learning classifier to predict the impression of posts to be greater than 1,000 based on the type of post, weekday or weekend, and weather.
When attempting to implement the classifier and test it using Python to calculate the precision and recall. I keep running into various errors including what's in the title.
Thank you.
Tutorial site reference:
Building Classification Model with Python by Rafi Atha
https://medium.com/analytics-vidhya/building-classification-model-with-python-9bdfc13faa4b

Keep model made with TFIDF for predicting new content using Scikit for Python

this is a sentiment analysis model made with tf-idf for feature extraction
i want to know how can i save this model and reuse it.
i tried saving it this way but when i load it , do same pre-processing on the test text and fit_transform on it it gave an error that the model expected X numbers of features but got Y
this is how i saved it
filename = "model.joblib"
joblib.dump(model, filename)
and this is the code for my tf-idf model
import pandas as pd
import re
import nltk
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
nltk.download('stopwords')
from nltk.corpus import stopwords
processed_text = ['List of pre-processed text']
y = ['List of labels']
tfidfconverter = TfidfVectorizer(max_features=10000, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))
X = tfidfconverter.fit_transform(processed_text).toarray()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
text_classifier = BernoulliNB()
text_classifier.fit(X_train, y_train)
predictions = text_classifier.predict(X_test)
print(confusion_matrix(y_test, predictions))
print(classification_report(y_test, predictions))
print(accuracy_score(y_test, predictions))
edit:
just to exact where to put every line
so after:
tfidfconverter = TfidfVectorizer(max_features=10000, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))
then
tfidf_obj = tfidfconverter.fit(processed_text)//this is what will be used again
joblib.dump(tfidf_obj, 'tf-idf.joblib')
then you do the rest of the steps you will save the classifier after training as well so after:
text_classifier.fit(X_train, y_train)
put
joblib.dump(model, "classifier.joblib")
now when you want to predict any text
tf_idf_converter = joblib.load("tf-idf.joblib")
classifier = joblib.load("classifier.joblib")
now u have List of sentences to predict
sent = []
classifier.predict(tf_idf_converter.transform(sent))
now print that for a list of sentiments for each sentece

You can first fit tfidf to your training set using:
tfidfconverter = TfidfVectorizer(max_features=10000, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))
tfidf_obj = tfidfconverter.fit(processed_text)
Then find a way to store the tfidf_obj for instance using pickle or joblib e.g:
joblib.dump(tfidf_obj, filename)
Then load the saved tfidf_obj and apply transform only on your test set
loaded_tfidf = joblib.load(filename)
test_new = loaded_tfidf.transform(X_test)

Feature Extraction for multiple text columns for classification problem

which is the correct way to extract features from multiple text columns and apply any classification algorithm on it?
please suggest me, if i am going wrong
example dataset
Independent Variables : Description1,Description2, State, NumericCol1,NumericCol2
Dependent Variable : TargetCategory
Code:
########### Feature Exttraction for Text Data #####################
######### Description1 (it can be any wordembedding technique like countvectorizer, tfidf, word2vec,bert..etc)
tfidf = TfidfVectorizer(max_features = 500,
ngram_range = (1,3),
stop_words = "english")
X_Description1 = tfidf.fit_transform(df["Description1"].tolist())
######### Description2 (it can be any wordembedding technique like countvectorizer, tfidf, word2vec,bert..etc)
tfidf = TfidfVectorizer(max_features = 500,
ngram_range = (1,3),
stop_words = "english")
X_Description2 = tfidf.fit_transform(df["Description2"].tolist())
######### State (have 100 unique entries thats why used BinaryEncoder)
import category_encoders as ce
binary_encoder= ce.BinaryEncoder(cols=['state'],return_df=True)
X_state = binary_encoder.fit_transform(df["state"])
import scipy
X = scipy.sparse.hstack((X_Description1,
X_Description2,
X_state,
df[["NumericCol1", "NumericCol2"]].to_numpy())).tocsr()
y = df['TargetCategory']
##### train Test Split ########
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8, random_state=111)
##### Create Model Model ######
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, recall_score, classification_report, cohen_kappa_score
from sklearn import metrics
# Baseline Random forest based Model
rfc = RandomForestClassifier(criterion = 'gini', n_estimators=1000, verbose=1, n_jobs = -1,
class_weight = 'balanced', max_features = 'auto')
rfcg = rfc.fit(X_train,y_train) # fit on training data
####### Prediction ##########
predictions = rfcg.predict(X_test)
print('Baseline: Accuracy: ', round(accuracy_score(y_test, predictions)*100, 2))
print('\n Classification Report:\n', classification_report(y_test,predictions))

The way to use multiple columns as input in scikit-learn is by using the ColumnTransformer.
Here is an example on how to use it with heterogeneous data.

Cross validation desicion tree

After making a desicion tree function, I have decided to check how accurate is the tree, and to confirm that atleast the first split is the same if I'll make another trees with the same data
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import os
from sklearn import tree
from sklearn import preprocessing
import sys
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
.....
def desicion_tree(data_set:pd.DataFrame,val_1 : str, val_2 : str):
#Encoder -- > fit doesn't accept strings
feature_cols = data_set.columns[0:-1]
X = data_set[feature_cols] # Independent variables
y = data_set.Mut #class
y = y.to_list()
le = preprocessing.LabelBinarizer()
y = le.fit_transform(y)
# Split data set into training set and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=1) # 75%
# Create Decision Tree classifer object
clf = DecisionTreeClassifier(max_depth= 4, criterion= 'entropy')
# Train Decision Tree Classifer
clf.fit(X_train, y_train)
# Predict the response for test dataset
y_pred = clf.predict(X_test)
#Perform cross validation
for i in range(2, 8):
plt.figure(figsize=(14, 7))
# Perform Kfold cross validation
#cv = ShuffleSplit(test_size=0.25, random_state=0)
kf = KFold(n_splits=5,shuffle= True)
scores = cross_val_score(estimator=clf, X=X, y=y, n_jobs=4, cv=kf)
print("%0.2f accuracy with a standard deviation of %0.2f" % (scores.mean(), scores.std()))
tree.plot_tree(clf,filled = True,feature_names=feature_cols,class_names=[val_1,val_2])
plt.show()
desicion_tree(car_rep_sep_20, 'Categorial', 'Non categorial')
Down , I wrote a loop in order to rectreate the tree with splitted values using Kfold. The accuracy is changing (around 90%) but the tree is the same, where did I mistaken?

cross_val_score clones the estimator in order to fit-and-score on the various folds, so the clf object remains the same as when you fit it to the entire dataset before the loop, and so the plotted tree is that one rather than any of the cross-validated ones.
To get what you're after, I think you can use cross_validate with option return_estimator=True. You also shouldn't need the loop, if your cv object has the number of splits desired:
kf = KFold(n_splits=5, shuffle=True)
cv_results = cross_validate(
estimator=clf,
X=X,
y=y,
n_jobs=4,
cv=kf,
return_estimator=True,
)
print("%0.2f accuracy with a standard deviation of %0.2f" % (
cv_results['test_score'].mean(),
cv_results['test_score'].std(),
))
for est in cv_results['estimator']:
tree.plot_tree(est, filled=True, feature_names=feature_cols, class_names=[val_1, val_2])
plt.show();
Alternatively, loop manually over the folds (or other cv iteration), fitting the model and plotting its tree in the loop.

Improve precision of my predictive technique in Python

I am using the following Python code to make output predictions depending on some values using decision trees based on entropy/gini index. My input data is contained in the file: https://drive.google.com/file/d/1C8GZ2wiqFUW3WuYxyc0G3axgkM1Uwsb6/view?usp=sharing
The first column "gold" in the file contains the output that I am trying to predict (either T or N). The remaining columns represents some 0 or 1 data that I can use to predict the first column. I am using a test set of 30% and a training set of 70%. I am getting the same precision/recall using either entropy or gini index. I am getting a precision of 0.80 for T and a recall of 0.54 for T. I would like to increase the precision of T and I am okay if the recall for T goes down as well, I am willing to accept this tradeoff. I do not care about the precision/recall of N predictions, I am just trying to improve the precision of T, that's all I care about. I guess increasing the precision means that we should abstain from making predictions in some situations that we are not certain about. How to do that?
# Run this program on your local python
# interpreter, provided you have installed
# the required libraries.
# Importing the required packages
import numpy as np
import pandas as pd
from sklearn.metrics import confusion_matrix
from sklearn.cross_validation import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.ensemble import ExtraTreesClassifier
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.externals.six import StringIO
from IPython.display import Image
from sklearn.tree import export_graphviz
from sklearn import tree
import collections
import pydotplus
# Function importing Dataset
column_count =0
def importdata():
balance_data = pd.read_csv( 'data1extended.txt', sep= ',')
row_count, column_count = balance_data.shape
# Printing the dataswet shape
print ("Dataset Length: ", len(balance_data))
print ("Dataset Shape: ", balance_data.shape)
print("Number of columns ", column_count)
# Printing the dataset obseravtions
print ("Dataset: ",balance_data.head())
return balance_data, column_count
def columns(balance_data):
row_count, column_count = balance_data.shape
return column_count
# Function to split the dataset
def splitdataset(balance_data, column_count):
# Separating the target variable
X = balance_data.values[:, 1:column_count]
Y = balance_data.values[:, 0]
# Splitting the dataset into train and test
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size = 0.3, random_state = 100)
return X, Y, X_train, X_test, y_train, y_test
# Function to perform training with giniIndex.
def train_using_gini(X_train, X_test, y_train):
# Creating the classifier object
clf_gini = DecisionTreeClassifier(criterion = "gini",
random_state = 100,max_depth=3, min_samples_leaf=5)
# Performing training
clf_gini.fit(X_train, y_train)
return clf_gini
# Function to perform training with entropy.
def tarin_using_entropy(X_train, X_test, y_train):
# Decision tree with entropy
clf_entropy = DecisionTreeClassifier(
criterion = "entropy", random_state = 100,
max_depth = 3, min_samples_leaf = 5)
# Performing training
clf_entropy.fit(X_train, y_train)
return clf_entropy
# Function to make predictions
def prediction(X_test, clf_object):
# Predicton on test with giniIndex
y_pred = clf_object.predict(X_test)
print("Predicted values:")
print(y_pred)
return y_pred
# Function to calculate accuracy
def cal_accuracy(y_test, y_pred):
print("Confusion Matrix: ",
confusion_matrix(y_test, y_pred))
print ("Accuracy : ",
accuracy_score(y_test,y_pred)*100)
print("Report : ",
classification_report(y_test, y_pred))
#Univariate selection
def selection(column_count, data):
# data = pd.read_csv("data1extended.txt")
X = data.iloc[:,1:column_count] #independent columns
y = data.iloc[:,0] #target column i.e price range
#apply SelectKBest class to extract top 10 best features
bestfeatures = SelectKBest(score_func=chi2, k=5)
fit = bestfeatures.fit(X,y)
dfscores = pd.DataFrame(fit.scores_)
dfcolumns = pd.DataFrame(X.columns)
df=pd.DataFrame(data, columns=X)
#concat two dataframes for better visualization
featureScores = pd.concat([dfcolumns,dfscores],axis=1)
featureScores.columns = ['Specs','Score'] #naming the dataframe columns
print(featureScores.nlargest(5,'Score')) #print 10 best features
return X,y,data,df
#Feature importance
def feature(X,y):
model = ExtraTreesClassifier()
model.fit(X,y)
print(model.feature_importances_) #use inbuilt class feature_importances of tree based classifiers
#plot graph of feature importances for better visualization
feat_importances = pd.Series(model.feature_importances_, index=X.columns)
feat_importances.nlargest(5).plot(kind='barh')
plt.show()
#Correlation Matrix
def correlation(data, column_count):
corrmat = data.corr()
top_corr_features = corrmat.index
plt.figure(figsize=(column_count,column_count))
#plot heat map
g=sns.heatmap(data[top_corr_features].corr(),annot=True,cmap="RdYlGn")
def generate_decision_tree(X,y):
clf = DecisionTreeClassifier(random_state=0)
data_feature_names = ['callersAtLeast1T','CalleesAtLeast1T','callersAllT','calleesAllT','CallersAtLeast1N','CalleesAtLeast1N','CallersAllN','CalleesAllN','childrenAtLeast1T','parentsAtLeast1T','childrenAtLeast1N','parentsAtLeast1N','childrenAllT','parentsAllT','childrenAllN','ParentsAllN','ParametersatLeast1T','FieldMethodsAtLeast1T','ReturnTypeAtLeast1T','ParametersAtLeast1N','FieldMethodsAtLeast1N','ReturnTypeN','ParametersAllT','FieldMethodsAllT','ParametersAllN','FieldMethodsAllN']
#generate model
model = clf.fit(X, y)
# Create DOT data
dot_data = tree.export_graphviz(clf, out_file=None,
feature_names=data_feature_names,
class_names=y)
# Draw graph
graph = pydotplus.graph_from_dot_data(dot_data)
# Show graph
Image(graph.create_png())
# Create PDF
graph.write_pdf("tree.pdf")
# Create PNG
graph.write_png("tree.png")
# Driver code
def main():
# Building Phase
data,column_count = importdata()
X, Y, X_train, X_test, y_train, y_test = splitdataset(data, column_count)
clf_gini = train_using_gini(X_train, X_test, y_train)
clf_entropy = tarin_using_entropy(X_train, X_test, y_train)
# Operational Phase
print("Results Using Gini Index:")
# Prediction using gini
y_pred_gini = prediction(X_test, clf_gini)
cal_accuracy(y_test, y_pred_gini)
print("Results Using Entropy:")
# Prediction using entropy
y_pred_entropy = prediction(X_test, clf_entropy)
cal_accuracy(y_test, y_pred_entropy)
#COMMENTED OUT THE 4 FOLLOWING LINES DUE TO MEMORY ERROR
#X,y,dataheaders,df=selection(column_count,data)
#generate_decision_tree(X,y)
#feature(X,y)
#correlation(dataheaders,column_count)
# Calling main function
if __name__=="__main__":
main()

I would suggest using Pipelines, to build data pipelines and GridSearchCV to find the best possible hyper-parameters and classifiers for the pipe.
A basic example;
from sklearn.tree import DecisionTreeClassifier
from sklearn.feature_selection import SelectKBest, chi2, f_class
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
pipe = Pipeline[('kbest', SelectKBest(chi2, k=3000)),
('clf', DecisionTreeClassifier())
])
pipe_params = {'kbest__k': range(1, 10, 1),
'kbest__score_func': [f_classif, chi2],
'clf__max_depth': np.arange(1,30),
'clf__min_samples_leaf': [1,2,4,5,10,20,30,40,80,100]}
grid_search = GridSearchCV(pipe, pipe_params, n_jobs=-1
scoring=accuracy_score, cv=10)
grid_search.fit(X_train, Y_train)
This will iterate over every hyper-parameters in pipe_params and choose the best classifier based on accuracy_score.