Created
July 28, 2018 15:18
-
-
Save nithyadurai87/8104cd2437391c8075fcbb16188e7b64 to your computer and use it in GitHub Desktop.
populations.py - for spark tutorial
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark.context import SparkContext | |
from pyspark.sql.session import SparkSession | |
from pyspark.sql.functions import col | |
from matplotlib import pyplot | |
from pyspark.ml.feature import VectorAssembler | |
from pyspark.sql.types import Row | |
from pyspark.ml.regression import LinearRegression | |
sc = SparkContext('local') | |
spark = SparkSession(sc) | |
df1 = spark.read.option('header','true')\ | |
.option('inferSchema','true')\ | |
.csv('file:///home/shrini/born_babies.csv') | |
print (df1) | |
print (df1.columns) | |
print (df1.toPandas()) | |
df2 = df1.groupBy('yr')\ | |
.agg({'male' : 'sum', 'female' : 'sum'})\ | |
.select(col('yr'), (col('sum(male)')+col('sum(female)')).alias('populations'))\ | |
.orderBy('yr') | |
print (df2.toPandas()) | |
pyplot.plot(df2.toPandas().yr, df2.toPandas().populations) | |
pyplot.xlabel('Year') | |
pyplot.ylabel('No. of babies') | |
pyplot.title('Population includes new born male and female babies') | |
pyplot.annotate('local max', xy=(2001, .0), xytext=(2002, 1.1), fontsize = 12,arrowprops=dict(facecolor='grey', shrink=0.05, linewidth = 2)) | |
pyplot.show() | |
train = VectorAssembler(inputCols=['yr'], outputCol = 'features').transform(df2)\ | |
.withColumn('year',df2.yr)\ | |
.withColumn('label',df2.populations) | |
print (train.toPandas()) | |
i = VectorAssembler(inputCols=['yr'], outputCol = 'features').transform(sc.parallelize(train.select('yr').rdd.map(lambda x: x[0]).collect()+[2019, 2020, 2021, 2022, 2023]).map(Row('yr')).toDF()) | |
model = LinearRegression(maxIter=10).fit(train).transform(i).toPandas() | |
print (model) | |
pyplot.plot(model.yr,model.prediction) | |
pyplot.plot(train.select('yr').rdd.map(lambda x: x[0]).collect(), train.select('populations').rdd.map(lambda x: x[0]).collect()) | |
pyplot.legend(loc = 4) | |
pyplot.title('Prediction on future population') | |
pyplot.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment