hello, I need help $,$ when i try to call my pipline i get an error:

from pyspark.ml$.$feature import VectorAssembler, OneHotEncoder, StringIndexer

from pyspark.ml$.$evaluation import MulticlassClassificationEvaluator

from pyspark.ml$.$classification import LogisticRegression, DecisionTreeClassifier

from pyspark.ml import Pipeline

# create lists of feature names

num$\_$features $=["$age$",$ "hypertension","heart$\_$disease", "avg$\_$glucose$\_$level", "bmi"$]$

cat$\_$features $=[$col for col in stroke$\_$df$.$columns if col not in num$\_$features $+["$stroke$"]]$

# create lists of integer$-$encoded and one$-$hot encoded features

ix$\_$features $=[$col $+"\_$ix$"$ for col in cat$\_$features$]$

vec$\_$features $=[$col $+"\_$vec" for col in cat$\_$features$]$

# create StringIndexer, OneHotEncoder, and VectorAssembler objects

indexer $=$ StringIndexer$($inputCols$=$cat$\_$features, outputCols$=$ix$\_$features, handleInvalid$=$"skip"$)$

encoder $=$ OneHotEncoder$($inputCols$=$ix$\_$features, outputCols$=$vec$\_$features$)$

assembler $=$ VectorAssembler$($inputCols$=$num$\_$features $+$ vec$\_$features, outputCol$=$"features"$)$

# create pipeline

pipeline $=$ Pipeline$($stages$=[$indexer$,$ encoder, assembler$])$

# fit pipeline to data

train $=$ pipeline.fit$($stroke$\_$df$).$transform$($stroke$\_$df$)$

# persist train DataFrame

train.persist$()$

# display first $10$ rows of features and stroke columns of train

train.select$("$features$",$ "stroke"$).$show$(10,$ truncate$=$False$)$

train $=$ train.withColumn$("$label$",$ train$["$stroke$"])$ Applying the Model to New Data : data $=\{$

"gender": $["$Female$",$ "Female", "Male", "Male"$],$

"age": $[42\mathrm{.}0,64\mathrm{.}0,37\mathrm{.}0,72\mathrm{.}0],$

"hypertension": $[1,1,0,0],$

"heart$\_$disease": $[0,1,0,1],$

"ever$\_$married": $["$No$",$ "Yes", "Yes", $"$No$"],$

"work$\_$type": $["$Private$",$ "Self$-$employed", "Private", "Govt$\_$job"$],$

"Residence$\_$type": $["$Urban$",$ "Rural", "Rural", "Urban"$],$

"avg$\_$glucose$\_$level": $[182\mathrm{.}1,175\mathrm{.}5,79\mathrm{.}2,125\mathrm{.}7],$

"bmi": $[26\mathrm{.}5,32\mathrm{.}5,15\mathrm{.}4,19\mathrm{.}4],$

"smoking$\_$status": $["$smokes$",$ "formerly smoked", "unknown", "never smoked"$]$

$\}$

new$\_$data $=$ pd$.$DataFrame$($data$)$

new$\_$data

processed$\_$new$\_$data $=$ pipeline.fit$($new$\_$data$).$transform$($new$\_$data$)$ : AttributeError: 'DataFrame' object has no attribute $\text{'}\_$jdf$\text{'}$

~$/.$ipykernel$/16918/$command$-472670917524769-290429957$ in $?()$

$---->1$ processed$\_$new$\_$data $=$ pipeline.fit$($new$\_$data$).$transform$($new$\_$data$)$

$/$databricks$/$python$/$lib$/$python$3\mathrm{.}10/$site$-$packages$/$pandas$/$core$/$generic$.$py in $?($self$,$ name$)$

$5898$ and name not in self.$\_$accessors

$5899$ and self.$\_$info$\_$axis.$\_$can$\_$hold$\_$identifiers$\_$and$\_$holds$\_$name$($name$)$

$5900)$:

$5901$ return self$[$name$]$

$->5902$ return object.$\_\_$getattribute$\_\_($self$,$ name$)$