Uploading_code_part_to_show

Code_part_to_show.txt

@@ -0,0 +1,272 @@
+import pandas as pd
+import numpy as np
+
+crop = pd.read_csv("Crop_recommendation.csv")
+crop.head()
+
+crop.info()
+
+# to check null value is present or not
+crop.isnull().sum()
+
+# to check duplicate value is present or not
+crop.duplicated().sum()
+
+# describe all the mathematical info of only numerical data
+# 25 % === percentile
+crop.describe()
+
+
+
+#Exploring Data correlation
+# corr = crop.corr()
+# corr
+# Select only numeric columns for correlation computation
+numeric_columns = crop.select_dtypes(include=['number'])
+# Compute the correlation matrix
+corr = numeric_columns.corr()
+corr
+
+
+
+
+import seaborn as sns
+sns.heatmap(corr , annot = True , cmap = 'coolwarm')
+
+
+
+crop['label'].value_counts()
+
+
+
+
+import matplotlib.pyplot as plt
+sns.distplot(crop['N'])
+plt.show()
+
+
+
+
+
+#Encoding
+crop_dict = {
+    'rice': 1,
+    'maize': 2,
+    'jute': 3,
+    'cotton': 4,
+    'coconut': 5,
+    'papaya': 6,
+    'orange': 7,
+    'apple': 8,
+    'muskmelon': 9,
+    'watermelon': 10,
+    'grapes': 11,
+    'mango': 12,
+    'banana': 13,
+    'pomegranate': 14,
+    'lentil': 15,
+    'blackgram': 16,
+    'mungbean': 17,
+    'mothbeans': 18,
+    'pigeonpeas': 19,
+    'kidneybeans': 20,
+    'chickpea': 21,
+    'coffee': 22
+}
+crop['crop_num'] = crop['label'].map(crop_dict)   # 'crop_num' kuch v name de sakte
+
+
+
+
+crop['crop_num'].value_counts()
+
+
+
+
+
+crop.drop('label' , axis = 1 , inplace = True)        # no need to do this
+crop.head(500)
+
+
+
+
+
+x = crop.drop('crop_num' , axis = 1)
+y = crop['crop_num']
+
+
+
+# Train Test Split
+from sklearn.model_selection import train_test_split
+x_train , x_test , y_train , y_test = train_test_split(x , y , test_size = 0.2 , random_state = 42)
+
+
+
+
+x_train.shape
+
+
+x_test.shape
+
+
+
+# Scale the features using MinMaxScaler
+from sklearn.preprocessing import MinMaxScaler
+ms = MinMaxScaler()
+
+# ms.fit(x_train)
+x_train = ms.fit_transform(x_train)
+x_test = ms.transform(x_test)
+
+
+
+
+
+
+
+# Standardization
+
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+
+# sc.fit(x_train)
+
+x_train = sc.fit_transform(x_train)
+x_test = sc.transform(x_test)
+
+
+
+
+
+
+
+# Training Models
+
+
+from sklearn.linear_model import LogisticRegression
+from sklearn.naive_bayes import GaussianNB
+from sklearn.svm import SVC
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.tree import ExtraTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import BaggingClassifier
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.ensemble import AdaBoostClassifier
+from sklearn.metrics import accuracy_score
+
+# create instances of all models
+models = {
+    'Logistic Regression': LogisticRegression(),
+    'Support Vector Machine': SVC(),
+    'K-Nearest Neighbors': KNeighborsClassifier(),
+    'Decision Tree': DecisionTreeClassifier(),
+    'Bagging': BaggingClassifier(),
+    'AdaBoost': AdaBoostClassifier(),
+    'Gradient Boosting': GradientBoostingClassifier(),
+    'Extra Trees': ExtraTreeClassifier(),
+    'Naive Bayes': GaussianNB(),
+    'Random Forest': RandomForestClassifier()
+}
+
+# md = model
+for name, md in models.items():
+    md.fit(x_train,y_train)
+    ypred = md.predict(x_test)
+    
+    print(f"{name}  with accuracy : {accuracy_score(y_test,ypred)}")
+
+
+
+
+
+
+
+
+
+
+rfc = RandomForestClassifier()
+rfc.fit(x_train,y_train)
+ypred = rfc.predict(x_test)
+accuracy_score(y_test,ypred)
+
+
+
+
+
+
+# Predictive System
+
+
+def recommendation(N,P,k,temperature,humidity,ph,rainfal):
+    features = np.array([[N,P,k,temperature,humidity,ph,rainfal]])
+    transformed_features = ms.transform(features)
+    transformed_features = sc.transform(transformed_features)
+    prediction = rfc.predict(transformed_features).reshape(1,-1)  # .reshape(1,-1) karne se single row ka o/p dega
+    
+    return prediction[0]       # returns {1,2,3,....,22}
+
+
+#The .reshape(1, -1) part reshapes the prediction array into a 2-dimensional array with 1 row and as many columns as necessary to fit the data
+  
+
+
+
+
+
+
+
+
+# N = 40
+# P = 50
+# k = 50
+# temperature = 40.0
+# humidity = 20.0
+# ph = 100.0
+# rainfall = 100.0
+
+
+# N = 30
+# P = 10
+# k = 100
+# temperature = 100.0
+# humidity = 210.0
+# ph = 100.0
+# rainfall = 23.0
+
+N = 30
+P = 20
+k = 150
+temperature = 23      # Best for apple
+humidity = 60
+ph = 5.5
+rainfall = 900
+
+predict = recommendation(N,P,k,temperature,humidity,ph,rainfall)
+
+
+crop_dict = {1: "Rice", 2: "Maize", 3: "Jute", 4: "Cotton", 5: "Coconut", 6: "Papaya", 7: "Orange",
+                 8: "Apple", 9: "Muskmelon", 10: "Watermelon", 11: "Grapes", 12: "Mango", 13: "Banana",
+                 14: "Pomegranate", 15: "Lentil", 16: "Blackgram", 17: "Mungbean", 18: "Mothbeans",
+                 19: "Pigeonpeas", 20: "Kidneybeans", 21: "Chickpea", 22: "Coffee"}
+
+if predict[0] in crop_dict:
+    crop = crop_dict[predict[0]]
+    print("{} is a best crop to be cultivated ".format(crop))
+else:
+    print("Sorry are not able to recommend a proper crop for this environment")
+
+
+
+
+
+
+
+import pickle
+pickle.dump(rfc , open('model.pkl' , 'wb'))           # wb = write binary
+# now 'model.pkl' is our model which can be used anywhere
+
+
+
+
+