import pandas as pd
import sklearn
import numpy as np
from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.ensemble import VotingClassifier,RandomForestClassifier
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt

data = pd.read_csv("L:\Gender classification\gender_classification_v7.csv")
data.head(20)
#checking for null values
data.isnull().sum()
data.describe()

#visualising forehead length data
sns.lineplot(data['forehead_width_cm'],data['forehead_height_cm'], hue=data["gender"])

#visualising nose length data
sns.lineplot(data['nose_long'],data['nose_wide'], hue=data["gender"])

twogender = {'Female':0, 'Male':1}
data['gender'] = data['gender'].map(twogender)

X = data.drop('gender', axis=1)
y = data['gender']

#splitting data for testing and traing process
from sklearn.model_selection import train_test_split, GridSearchCV
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.3)
print(X_train.shape)
print(X_val.shape)
print(y_train.shape)
print(y_val.shape)

from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, plot_confusion_matrix
from sklearn.ensemble import RandomForestClassifier

dt = DecisionTreeClassifier(random_state=0)

dt.fit(X_train, y_train)
dt_pred = dt.predict(X_val)
dt_acc = accuracy_score(y_val, dt_pred)
print('Accuracy of Decision Tree is: {:.2f}%'.format(dt_acc*100))

rf = RandomForestClassifier(random_state=0)

rf.fit(X_train, y_train)
rf_pred = rf.predict(X_val)
rf_acc = accuracy_score(y_val, rf_pred)
print('Accuracy of Random Forest is: {:.2f}%'.format(rf_acc*100))

lr = LogisticRegression(random_state=0)

lr.fit(X_train, y_train)
lr_pred = lr.predict(X_val)
lr_acc = accuracy_score(y_val, lr_pred)
print('Accuracy of Logistic Regression is: {:.2f}%'.format(lr_acc*100))

knn = KNeighborsClassifier()
params = {'n_neighbors':[2,3,4,5,6,7,8,9]}

model = GridSearchCV(knn, params, cv=5)
model.fit(X_train, y_train)
model.best_params_

kn = KNeighborsClassifier(n_neighbors=8)

kn.fit(X_train, y_train)
kn_pred = kn.predict(X_val)
kn_acc = accuracy_score(y_val, kn_pred)
print('Accuracy of KNeighbors is: {:.2f}%'.format(kn_acc*100))

import pandas as pd
import sklearn
import numpy as np
from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.ensemble import VotingClassifier,RandomForestClassifier
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import confusion_matrix

data = pd.read_csv("L:\Gender classification\gender_classification_v7.csv")

#encoding data
twogender = {'Female':0, 'Male':1}
data['gender'] = data['gender'].map(twogender)

X = data.drop('gender', axis=1)
y = data['gender']

#splitting data for testing and traing process
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import accuracy_score, plot_confusion_matrix


X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.3)

from sklearn.ensemble import RandomForestClassifier
#randomforestClassifier 
rf = RandomForestClassifier(random_state=0)

rf.fit(X_train, y_train)
rf_pred = rf.predict(X_val)
rf_acc = accuracy_score(y_val, rf_pred)
print('Accuracy of Random Forest is: {:.2f}%'.format(rf_acc*100))

#pickeling model
import pickle
pickle.dump(rf,open("model.pkl","wb"))

model =pickle.load(open("model.pkl","rb"))