shashwatwork

# LSTM for sequence classification in the IMDB dataset
import numpy
from keras.datasets import imdb
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
# fix random seed for reproducibility
numpy.random.seed(7)

shashwatwork

from __future__ import print_function
import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
import os

batch_size = 32

shashwatwork

# Load Datasets
df_train  = pd.read_csv('../input/train.csv')
df_test   = pd.read_csv('../input/test.csv')
df_submit = pd.read_csv('../input/sample_submission.csv')

# To numpy array - dataset of train
x_all = df_train.drop(['target', 'id'], axis=1).values
y_all = keras.utils.np_utils.to_categorical(df_train['target'].values)

# For imbalanced data, better-way maybe exist!

shashwatwork

# Example from Sklean Doc
from sklearn.cluster import DBSCAN
import numpy as np
X = np.array([[1, 2], [2, 2], [2, 3],[8, 7], [8, 8], [25, 80]])
clustering = DBSCAN(eps=3, min_samples=2).fit(X)
clustering.labels_
array([ 0,  0,  0,  1,  1, -1])
print(clustering) 
DBSCAN(algorithm='auto', eps=3, leaf_size=30, metric='euclidean',
    metric_params=None, min_samples=2, n_jobs=None, p=None)

shashwatwork

#Import Library
from sklearn.cluster import KMeans
#Assumed you have, X (attributes) for training data set and x_test(attributes) of test_dataset
# Create KNeighbors classifier object model 
k_means = KMeans(n_clusters=3, random_state=0)
# Train the model using the training sets and check score
model.fit(X)
#Predict Output
predicted= model.predict(x_test)

shashwatwork

from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
X = dataset[:,0:10]
Y = dataset[:,10:]
seed = 1

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=seed)

model = XGBClassifier()

shashwatwork

#Import Library
from sklearn.ensemble import GradientBoostingClassifier
#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset
# Create Gradient Boosting Classifier object
model= GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0)
# Train the model using the training sets and check score
model.fit(X, y)
#Predict Output
predicted= model.predict(x_test)
print(predicted)

shashwatwork

from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import numpy as np
iris=load_iris()
df=pd.DataFrame(iris.data,columns=iris.feature_names)
df['is_train']=np.random.uniform(0,1,len(df))<=.75
df['species']=pd.Categorical.from_codes(iris.target,iris.target_names)
train,test=df[df['is_train']==True],df[df['is_train']==False]
features=df.columns[:4]

shashwatwork

from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn import datasets
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
iris=datasets.load_iris()
x=iris.data
y=iris.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=0)
gnb=GaussianNB()

shashwatwork

#Import Library
from sklearn import svm
#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset
# Create SVM classification object 
model = svm.svc() # there is various option associated with it, this is simple for classification. You can refer link, for mo# re detail.
# Train the model using the training sets and check score
model.fit(X, y)
model.score(X, y)
#Predict Output
predicted= model.predict(x_test)