jamespaultg

For example to install birch package:

1.	Download birch_1.2-3.tar.gz from https://cran.r-project.org/src/contrib/Archive/birch/. 

2.	Install rtools on windows following this  http://jtleek.com/modules/01_DataScientistToolbox/02_10_rtools/#6
3.	After installation, check if the windows environment variable PATH contains Rtools and gcc
You can check from within R by grepl("Rtools",Sys.getenv("PATH")). Should return TRUE. Or use grep("Rtools", strsplit(Sys.getenv("PATH"), ";")[[1]],value=TRUE) to display the path of Rtools if present in the PATH variable.
If not then use the following code to add the PATH.

# If the rtools path is not added in the environment variable PATH

jamespaultg

--Get the last date of the previous year (31-Dec-yyyy)
select trunc(current_date, 'yyyy')-1 from dual;

-- Get the first date of the previous year (01-Jan-yyyy)
select add_months(trunc(current_date, 'yyyy'),-12) from dual;

jamespaultg

pip3 install <package_name> --proxy <proxy_server:port>

jamespaultg

# Imagine you have more than two sets and you would want to find the overlapping elements in different sets
# and you would like to see the overlap using VennDiagram
require(VennDiagram)
library(gplots)
library(reshape2)


# We have three different dataframes with the customer-id as Key, and some additional fields
set1 = data.frame(Key = c(100,200,300), place = c('NY','IS','AZ'))
set2 = data.frame(Key = c(200,300,400), val2 = c(12,12,53))

jamespaultg

# visualise the decision tree

from sklearn.externals.six import StringIO  
from IPython.display import Image  
from sklearn.tree import export_graphviz
import pydotplus
dot_data = StringIO()

# ensure that variable tree has the decision tree, and features contains the names of the features

jamespaultg

from sklearn.tree import DecisionTreeClassifier, export_graphviz
tree = DecisionTreeClassifier(max_depth=3,random_state=0)
tree.fit(X_train,y_train)
plt.figure(figsize=(20, 10))
indices = np.argsort(tree.feature_importances_)[::-1]
#indices = np.argsort(tree.feature_importances_)[::1]

# Visualise the importance of the features
# To get your top 10 feature names
features_sorted = []

jamespaultg

from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler

SVCpipe = Pipeline([('scale', StandardScaler()),
                   ('SVC',LinearSVC())])

# Gridsearch to determine the value of C
param_grid = {'SVC__C':np.arange(0.01,100,10)}

jamespaultg

# Logistic regression
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler

logregpipe = Pipeline([('scale', StandardScaler()),
                   ('logreg',LogisticRegression(multi_class="multinomial",solver="lbfgs"))])

# Gridsearch to determine the value of C