gauravgola96

import numpy as np

# sigmoid function

def nonlin(x,deriv=False):

if(deriv==True):
return x*(1-x)
return 1/(1+np.exp(-x))
 

gauravgola96

# imputing missing values

train['Item_Visibility'] = train['Item_Visibility'].replace(0,np.mean(train['Item_Visibility']))

train['Outlet_Establishment_Year'] = 2013 - train['Outlet_Establishment_Year']

train['Outlet_Size'].fillna('Small',inplace=True)

# creating dummy variables to convert categorical into numeric values

gauravgola96

from csv import reader
import numpy as np
from random import seed
from sklearn.ensemble import BaggingClassifier, RandomForestClassifier
from sklearn.model_selection import cross_val_score

## Pre-processing functions
# Load a CSV file
def load_csv(filename):
	dataset = list()

gauravgola96

import pandas as pd
import numpy as np

train = pd.read_csv("C:\\Users\\Gaurav_Gola\\Desktop\\project\\black friday\\train.csv")

test = pd.read_csv("C:\\Users\\Gaurav_Gola\\Desktop\\project\\black friday\\test.csv")

train.shape

gauravgola96

import pandas as pd
import seaborn as sns 
import numpy as np 
import matplotlib.pylab as plt


# for plotting graphs in notebook 

%pylab inline 

gauravgola96

train = read.csv("C:\\Users\\Gaurav_Gola\\Desktop\\project\\loan prediction\\train.csv",na.strings = c(""," ",NA))
test = read.csv("C:\\Users\\Gaurav_Gola\\Desktop\\project\\loan prediction\\test.csv",na.strings = c(""," ",NA))

library(mlr)
summarizeColumns(train)
summarizeColumns(test)

#Data visualization
# for Character 

gauravgola96

library(ggplot2)
library(readr)

HREmployeeAttritionwithDefinitions <- read.csv("C:\\Users\\Gaurav_Gola\\Desktop\\project\\HR\\HR.csv",header = TRUE)
hr_data = HREmployeeAttritionwithDefinitions

#hr_data = read_csv("C:/Users/Rajat/Documents/R/HREmployeeAttritionwithDefinitions.csv")
summary(hr_data)

summary(table(hr_data$EmployeeCount))

gauravgola96

# House prize prediction

train = read.csv("train.csv",stringsAsFactors = F)
test = read.csv("test.csv",stringsAsFactors = F)

#checking the levels of variables in test and train datasets , they should be equal 
#checking character variables 

gauravgola96

import pandas as pd

train = pd.read_csv("C:\\Users\\Gaurav_Gola\\Desktop\\Praxis\\text\\my work\\Project\\train1.csv")

test = pd.read_csv("C:\\Users\\Gaurav_Gola\\Desktop\\Praxis\\text\\my work\\Project\\test.csv")

train.head() # lables are insult 
# 1 = insult
# 0 = not insult

gauravgola96

import tensorflow as tf

import numpy as np

tf.reset_default_graph()

sess = tf.Session()

x_vals = np.random.normal(loc=0.0,scale=0.1,size=100)
x_vals.shape