Niketkumardheeryan · priyankeshh · Jun 22, 2024 · Jun 22, 2024
diff --git a/Anime Data Analysis and Prediction/Dataset/All_Anime.csv b/Anime Data Analysis and Prediction/Dataset/All_Anime.csv
diff --git a/Anime Data Analysis and Prediction/Images/Box plot pr year.png b/Anime Data Analysis and Prediction/Images/Box plot pr year.png
diff --git a/Anime Data Analysis and Prediction/Images/Heatmap.png b/Anime Data Analysis and Prediction/Images/Heatmap.png
diff --git a/Anime Data Analysis and Prediction/Images/Histograms.png b/Anime Data Analysis and Prediction/Images/Histograms.png
diff --git a/Anime Data Analysis and Prediction/Images/Normal Distributions.png b/Anime Data Analysis and Prediction/Images/Normal Distributions.png
diff --git a/Anime Data Analysis and Prediction/Images/Pairplot.png b/Anime Data Analysis and Prediction/Images/Pairplot.png
diff --git a/Anime Data Analysis and Prediction/Model/anime_analysis_and_prediction.ipynb b/Anime Data Analysis and Prediction/Model/anime_analysis_and_prediction.ipynb
diff --git a/Anime Data Analysis and Prediction/Model/model_1.pkl b/Anime Data Analysis and Prediction/Model/model_1.pkl
diff --git a/Anime Data Analysis and Prediction/Model/model_2.pkl b/Anime Data Analysis and Prediction/Model/model_2.pkl
diff --git a/Anime Data Analysis and Prediction/Readme.md b/Anime Data Analysis and Prediction/Readme.md
@@ -0,0 +1,66 @@
+## Title: Anime Data Analysis and Prediction
+
+## Goal: To analyze the Anime Dataset using Exploratory Data Analysis using several parameters and then try to make predictions
+
+## Dataset link:
+https://www.kaggle.com/datasets/ayush4807/aad-dataset
+
+## Techniques used: 
+1. Data Filtering
+2. Data Preprocessing
+3. Data Extraction
+4. Data visualization
+5. Data Modelling
+6. Pickling the model
+
+## Libraries used:
+1. Pandas
+2. Pandas profiling
+3. Numpy 
+4. Matplotlib
+5. Scikit Learn
+6. Pickle
+
+## Data visuals created:
+1. Hsitogram
+2. Box plot
+3. Scatter Plot
+4. Bar plot
+5. Heatmap
+6. Pairplot
+
+## Machine Learning Models used:
+1. Linear Regression
+2. Decsion Tree Regression
+3. Random Forest Regressor
+
+## Evaluation metrics used:
+1. Root Mean Squared error
+2. Mean Squared error
+3. R2 score
+4. Training Score
+
+## Visuals:
+<img src = "https://github.com/PiyushBL45t/ML-Crate/blob/main/Anime%20Data%20Analysis%20and%20Prediction/Images/Box%20plot%20pr%20year.png"/>
+<img src = "https://github.com/PiyushBL45t/ML-Crate/blob/main/Anime%20Data%20Analysis%20and%20Prediction/Images/Heatmap.png"/>
+<img src = "https://github.com/PiyushBL45t/ML-Crate/blob/main/Anime%20Data%20Analysis%20and%20Prediction/Images/Histograms.png"/>
+<img src = "https://github.com/PiyushBL45t/ML-Crate/blob/main/Anime%20Data%20Analysis%20and%20Prediction/Images/Normal%20Distributions.png"/>
+<img src = "https://github.com/PiyushBL45t/ML-Crate/blob/main/Anime%20Data%20Analysis%20and%20Prediction/Images/Pairplot.png"/>
+
+## Conclusion
+### We tried to implement three model on our analyzed data. 
+#### 1. Linear Regression
+#### 2. Decision Tree Regressor
+#### 3. Random Forest Regressor
+
+### This was a continuous data thus, we applied the Regression Algorithms for this purpose.
+### The training paramter was "Rating": This depicts the Anime ratings on scale of 10. We trained and tested our model with two random types of Anime Genres: 
+#### 1. Animation, Adventure, Drama
+#### 2. Animation, Comedy, Fantasy
+## Results say that:
+### 1. Linear Regression and Random Forest Algorithms show a very low training score and a high error values and due to which they are not the best fit models. The predictions of <u>Ratings</u> based on those models is also very low for the future years.
+### 2. The Decision Tree on the other hand makes a very good predictions of ratings and we can say that the type of Animes we selected can catch more attention of audiences in the coming years. The evaluation metrics are stable and error results are very low this makes it fit to create a good predictive analysis example.
+
+## Authors
+
+- Created by [@Priyankesh](https://github.com/priyankeshh), GSSoC 2024
diff --git a/CS_GO Round Winner Classification/Dataset/csgo.csv b/CS_GO Round Winner Classification/Dataset/csgo.csv
diff --git a/CS_GO Round Winner Classification/Images/images1.png b/CS_GO Round Winner Classification/Images/images1.png
diff --git a/CS_GO Round Winner Classification/Images/images2.png b/CS_GO Round Winner Classification/Images/images2.png
diff --git a/CS_GO Round Winner Classification/Images/images3.png b/CS_GO Round Winner Classification/Images/images3.png
diff --git a/CS_GO Round Winner Classification/Images/images4.png b/CS_GO Round Winner Classification/Images/images4.png
diff --git a/CS_GO Round Winner Classification/Model/CS_GO_Round_Winner_Classification.ipynb b/CS_GO Round Winner Classification/Model/CS_GO_Round_Winner_Classification.ipynb
diff --git a/CS_GO Round Winner Classification/Model/README.md b/CS_GO Round Winner Classification/Model/README.md
@@ -0,0 +1,67 @@
+# PROJECT TITLE
+
+CS:GO Round Winner Classification
+
+## GOAL
+
+**Aim** - Predict who wins individual snapshots of rounds
+
+## DATASET
+
+https://www.kaggle.com/christianlillelund/csgo-round-winner-classification
+
+## DESCRIPTION
+
+This is a classification problem where we we predict who wins individual snapshots of rounds. We use Logistic Regression, Decision Tree and Random Forest Classifier
+
+## WHAT I HAD DONE
+
+1. Perfromed exploratory data analysis (EDA) on the given dataset
+2. It starts with loading the dataset and viewing the top 5 rows
+3. We calculate statistical data in the dataset
+4. Then comes finding correlation between the features and also finding statistical values related to the dataset
+5. Data visualization is done with libraries such as matplotlib and seaborn
+6. Finally 3 different algorithms are used to find the best algorithm 
+7. Also accuracy score of each algorithm is calculated for comparison purpose with other algorithms
+
+ DATA VISUALIZATION
+
+![image](https://user-images.githubusercontent.com/78292851/157266387-e42175ca-d73c-44de-acfa-bea89a24c0c7.png)
+
+![image](https://user-images.githubusercontent.com/78292851/157266436-8e3a1a69-d194-45fb-9d53-53fbf25f9698.png)
+
+![image](https://user-images.githubusercontent.com/78292851/157266484-b75f55c4-c8a3-4cd4-963a-6f298ce07939.png)
+
+
+
+
+## MODELS USED
+
+1. Logistic Regression= simplest and most common algorithm used for classification problems
+2. Decision Tree
+3. Random Forest Classifier
+
+
+## LIBRARIES NEEDED
+
+1. Numpy
+2. Pandas
+3. Matplotlib
+4. Seaborn
+5. Scikit-Learn
+
+## ACCURACIES
+
+1. Logistic Regression Score = 73.76%
+2. Random Forest Classifier = 88%
+3. Decision Tree- 81.96%
+
+## CONCLUSION
+
+We can conclude that Random Forest Classifier gives the most accurate results specifically for this problem statement.
+
+## Authors
+
+- Created by [@Priyankesh](https://github.com/priyankeshh), GSSoC 2024
+
+
diff --git a/CS_GO Round Winner Classification/requirements.txt b/CS_GO Round Winner Classification/requirements.txt
@@ -0,0 +1,5 @@
+matplotlib==3.9.0
+seaborn==0.13.2
+numpy==1.26.4
+pandas==2.2.2
+scikit_learn==1.5.0