def _model(self):
if self.family == GAUSSIAN_:
reg = LinearRegression()
elif self.family == BINOMIAL_:
reg = GeneralizedLinearRegression(family="binomial", link="logit")
else:
raise NotImplementedError("Family '{}' not implemented".format(
self.family))
reg.setLabelCol(self.response)
reg.setMaxIter(self.__max_iter)
return reg
sc = SparkContext()
sqlContext = SQLContext(sc)
spark = sqlContext.sparkSession
app = Flask(__name__)
model = None
gpa_df = sqlContext.read.load("./gpa_data.csv",
format='com.databricks.spark.csv',
header='true',
inferSchema='true')
lr = LinearRegression(maxIter=20)
lr.setFeaturesCol("hs_gpa_vector")
lr.setLabelCol("c_gpa")
assembler = VectorAssembler(inputCols=["hs_gpa"], outputCol="hs_gpa_vector")
output = assembler.transform(gpa_df)
split = output.randomSplit([0.7, 0.3])
@app.route('/home')
def doHome():
return 'Hello, World!'
@app.route('/train')
def doTrain():
global model
# In[9]:
print(vectorizer.explainParams())
# In[10]:
from pyspark.ml.regression import LinearRegression
# In[11]:
lr = LinearRegression()
print(lr.explainParams())
# In[12]:
lr.setLabelCol("EP")
lr.setFeaturesCol("features")
model = lr.fit(df_vect)
# In[13]:
type(model)
# In[14]:
print("R2:", model.summary.r2)
print("Intercept: ", model.intercept, "Coefficients", model.coefficients)
# In[15]:
df_pred = model.transform(df_vect)