MartinMacharia

import cx_Oracle
import pandas as pd
import csv

ip = '**********'
port = ****
SID = '********'
dsn_tns = cx_Oracle.makedsn(ip, port, SID)
conn = cx_Oracle.connect('DB_USERNAME', 'DB_PASSWORD', dsn_tns)
c = conn.cursor()

MartinMacharia

rom pandas.io.json import json_normalize
import json
import psycopg2
import pandas as pd
import requests
mm_get = requests.get('https://edume-api.herokuapp.com/stats/users',headers={"Authorization":'XXXXXXXXXXXXXXXXXXXXXXX'})mm_json=mm_get.json()
mm_json=mm_get.json()
data_1 = json_normalize(data         = mm_json['data'],
                       record_path   = ['courses','modules'],
                       record_prefix = 'courses.modules.',

MartinMacharia

view: edume_lessons {
  derived_table: {
    sql:
SELECT
    courses_modules_completiondate,
    courses_modules_id,
    courses_modules_status,
    courses_modules_title,
    courses_id,
    courses_title,

MartinMacharia

#CAST
Visit....Google Cast (Beta)
https://chrome.google.com/webstore/detail/google-cast-beta/dliochdbjfkdbacpmhlcpmleaejidimm?hl=en
Add to chrome
#Stitch
https://blog.stitchdata.com/google-sheets-stitch-an-easy-way-sync-your-small-data-to-redshift-32a32ece8e0a

MartinMacharia

---
output: word_document
---

# Plantwise data analysis

Data from PlantWise Kenya

## Comments on data 
+ ClinicFormID doesn't show in my file when opened in Excel (no text, just empty cells) - could there be more missing fields?

MartinMacharia

#EDA OFRA Spatial
#load neccessary packages
library(maptools)
library(sp)
library(rgdal)


#Importing data;
#maptools: Tools for Reading and Handling Spatial Objects
#rgdal has issues with IDs when importing spatial objects

MartinMacharia

#lOGIT

setwd("c:/Users/machariam/Desktop/Logit")
list.files()
Dat=read.csv("Dat.csv")
names(Dat)
str(Dat)
hist(LandPercapita)
hist(MaizeLand)
hist(PPI)

MartinMacharia

#Box plot

#Colour

setwd("c:/Users/machariam/Desktop/Rwanda PW Impact report/Logit")

list.files()

Dat.Yield=read.csv("Dat.Yield.csv")

MartinMacharia

data=read.csv(file.choose(), header=T) # Import data called data
View(data)# View data
duplicated(data$Dup) #Check for duplicates on column Dup, not a very efficient way for large dataset
data$Dup[duplicated(data1$Dup)] #Show duplicate entries, somewhat difficult to read results
unique(data1[duplicated(data1$Dup),])#Better way of showing unique repeat entries

#PSM with different matching criteria, select best based on visual inspection of common support graphics

setwd("C:/users/machariam/Desktop/Rwanda PW Impact report")
getwd()

MartinMacharia

data=read.csv(file.choose(), header=T) # Import data called data
View(data)# View data
duplicated(data$Dup) #Check for duplicates on column Dup, not a very efficient way for large dataset
data$Dup[duplicated(data1$Dup)] #Show duplicate entries, don't like how results are displayed
unique(data1[duplicated(data1$Dup),])#Better way of showing unique repeat entries

#PSM
setwd("C:/users/machariam/Desktop/Rwanda PW Impact report")
getwd()
RwandaData=read.csv("CleanV4.csv")